{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":797,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":797,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"a62c199a1ef5","filters":{"topic":"Sentiment Analysis and Opinion Mining"}},"results":[{"id":"W2084046180","doi":"10.1162/coli_a_00049","title":"Lexicon-Based Methods for Sentiment Analysis","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3255,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto; Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentiment analysis; Lexicon; Polarity (international relations); Natural language processing; Artificial intelligence; Negation; Consistency (knowledge bases); Orientation (vector space); Word (group theory); Process (computing); Reliability (semiconductor); Linguistics; Mathematics","authors":[{"name":"Maite Taboada","is_ca":true},{"name":"Julian Brooke","is_ca":true},{"name":"Milan Tofiloski","is_ca":true},{"name":"Kimberly Voll","is_ca":true},{"name":"Manfred Stede","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08804081832030412,"gpt":0.3846883079456333,"spread":0.2966474896253292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003045297,0.002071719,0.001542029,0.00900719,0.001419174,0.005393651,0.001823081,0.001376727,0.01292896],"category_scores_gemma":[0.01324147,0.0008683114,0.001970728,0.007577281,0.001017084,0.003788876,0.002279578,0.002361283,0.01427426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146294,"about_ca_system_score_gemma":0.001608836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00181939,"about_ca_topic_score_gemma":0.002607475,"domain_scores_codex":[0.9958007,0.001542527,0.0004785838,0.0006362508,0.001407892,0.0001340198],"domain_scores_gemma":[0.9944744,0.002982128,0.0004846158,0.0007069867,0.001249119,0.0001027838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001124247,0.0001679984,0.001888367,0.001421571,0.0004368785,0.0002571791,0.0006165473,0.008685959,0.01040488,0.1033624,0.06512037,0.8075254],"study_design_scores_gemma":[0.0001185435,0.00009532741,0.003233535,0.00053438,0.0002462578,0.0006830376,0.000772229,0.3646254,0.009748445,0.3800164,0.2397301,0.0001962019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001288293,0.001431312,0.9831582,0.0003887857,0.0003100782,0.000406241,0.002149259,0.003022652,0.007845165],"genre_scores_gemma":[0.04533688,0.002230737,0.936375,0.0003902522,0.0005900786,0.001292801,0.007213166,0.000841814,0.005729201],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01292896,"threshold_uncertainty_score":0.04325169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040467972","doi":"10.1111/j.1467-8640.2012.00460.x","title":"CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON","year":2012,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2584,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Lexicon; Crowdsourcing; Computer science; Annotation; Word (group theory); Natural language processing; Polarity (international relations); Term (time); Sentiment analysis; Association (psychology); Artificial intelligence; Quality (philosophy); Psychology; Linguistics; World Wide Web","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Peter D. Turney","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03803301095524386,"gpt":0.2981967277978994,"spread":0.2601637168426555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006199582,0.001406892,0.0009753044,0.005771454,0.002336238,0.002806749,0.00130232,0.001190452,0.006337135],"category_scores_gemma":[0.0290142,0.0005766068,0.001259952,0.004008322,0.001156701,0.00319832,0.004650285,0.001689884,0.004142233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001580819,"about_ca_system_score_gemma":0.002594051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004063209,"about_ca_topic_score_gemma":0.007677818,"domain_scores_codex":[0.9925218,0.003229932,0.0005862102,0.001208027,0.002185818,0.0002680816],"domain_scores_gemma":[0.9810643,0.009648737,0.001117331,0.002770295,0.004849118,0.000550241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001650195,0.0008002233,0.02015712,0.00253606,0.00041115,0.001888631,0.01182904,0.02388756,0.1046372,0.0509766,0.1448791,0.6363473],"study_design_scores_gemma":[0.0004742019,0.0003897514,0.02468498,0.0005795439,0.0003729106,0.0009486367,0.0108412,0.3581952,0.05164614,0.1993568,0.3520466,0.000464031],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1321987,0.0008602703,0.7681553,0.00443903,0.001425265,0.004171505,0.01999146,0.007718172,0.06104025],"genre_scores_gemma":[0.504193,0.000529061,0.4399024,0.001289259,0.0005178986,0.004337996,0.02791705,0.001374388,0.01993894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006337135,"threshold_uncertainty_score":0.03278691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2023736093","doi":"10.3758/s13428-012-0314-x","title":"Norms of valence, arousal, and dominance for 13,915 English lemmas","year":2013,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1978,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Psychology; Valence (chemistry); Stimulus (psychology); Taboo; Cognitive psychology; Arousal; Linguistics; Social psychology; Sociology","authors":[{"name":"Amy Beth Warriner","is_ca":true},{"name":"Victor Kuperman","is_ca":true},{"name":"Marc Brysbaert","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2235629719078966,"gpt":0.5275938138999604,"spread":0.3040308419920638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001951911,0.0003314141,0.0003496875,0.002050172,0.0006952198,0.001293661,0.0002317534,0.0002650147,0.004568661],"category_scores_gemma":[0.01732186,0.0001288054,0.0002262209,0.002466502,0.0005368649,0.0008428483,0.000513543,0.000342393,0.001449514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006726256,"about_ca_system_score_gemma":0.0004569102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003580639,"about_ca_topic_score_gemma":0.005022219,"domain_scores_codex":[0.9977425,0.0008713886,0.0004809325,0.0003428538,0.0004461693,0.0001162676],"domain_scores_gemma":[0.974816,0.01981295,0.001533519,0.0006141239,0.002951572,0.0002719356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0057725,0.0003815058,0.6022362,0.003161024,0.0004234866,0.001863899,0.03069177,0.001855208,0.04021695,0.01231182,0.03131493,0.2697708],"study_design_scores_gemma":[0.0001396097,0.0007411871,0.8824816,0.0004344442,0.0003324773,0.001974592,0.01330764,0.005313623,0.01335289,0.003590707,0.07820612,0.0001251919],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9622657,0.001096839,0.004144818,0.0001448938,0.0000955308,0.0001030373,0.01928642,0.0001399167,0.01272288],"genre_scores_gemma":[0.977536,0.0003773462,0.003635597,0.00003786656,0.00003438392,0.0001993452,0.01590992,0.00009917166,0.002170309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004568661,"threshold_uncertainty_score":0.0152837,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949998441","doi":"10.48550/arxiv.cs/0212032","title":"Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews","year":2002,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1585,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Phrase; Orientation (vector space); Natural language processing; Word (group theory); Computer science; Artificial intelligence; Linguistics; Mathematics","authors":[{"name":"Peter D. Turney","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1540121900601793,"gpt":0.3315217737850789,"spread":0.1775095837248996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001847947,0.0009526332,0.0009915725,0.003782591,0.000514595,0.001237109,0.0007267687,0.0009406521,0.00124614],"category_scores_gemma":[0.007626206,0.0002559335,0.000724351,0.002289648,0.0005725659,0.001065153,0.0005754678,0.0007130097,0.00105544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006907909,"about_ca_system_score_gemma":0.0008064743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002751257,"about_ca_topic_score_gemma":0.003142884,"domain_scores_codex":[0.9983795,0.0004488662,0.0001829009,0.0004062424,0.0004570645,0.0001254079],"domain_scores_gemma":[0.9969236,0.001592105,0.0004820354,0.0001934373,0.0007345355,0.00007423096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004887125,0.000248037,0.03791559,0.000293472,0.0003183185,0.0001654629,0.0004898616,0.0165499,0.01434355,0.003833491,0.008973823,0.9163799],"study_design_scores_gemma":[0.00008389108,0.0002250126,0.03847459,0.000105276,0.0001490144,0.0005221175,0.0004053469,0.9183896,0.0132675,0.02132189,0.006966904,0.000088957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2431534,0.001509253,0.7381621,0.0009997576,0.0003447286,0.0006575873,0.001400648,0.003879878,0.009892613],"genre_scores_gemma":[0.7380538,0.0003737356,0.2568479,0.0002424737,0.0003228698,0.000285121,0.001362897,0.0001097075,0.00240155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003782591,"threshold_uncertainty_score":0.009773016,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168625136","doi":"10.1145/944012.944013","title":"Measuring praise and criticism","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1509,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Aeronautics and Space Administration","keywords":"Computer science; Praise; Natural language processing; Artificial intelligence; Orientation (vector space); Pointwise mutual information; Noun; Set (abstract data type); Word (group theory); Latent semantic analysis; Criticism; Semantics (computer science); Linguistics; Psychology; Mutual information; Mathematics","authors":[{"name":"Peter D. Turney","is_ca":true},{"name":"Michael L. Littman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03905183252988257,"gpt":0.2486251028607023,"spread":0.2095732703308197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003876772,0.0004644166,0.0004027832,0.003016293,0.000478445,0.001762202,0.0004679903,0.000798494,0.002112851],"category_scores_gemma":[0.03181303,0.0001739217,0.0005030372,0.001733218,0.001264526,0.001912088,0.001671489,0.0008936687,0.0007852385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006829122,"about_ca_system_score_gemma":0.0004273902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006580116,"about_ca_topic_score_gemma":0.0009657931,"domain_scores_codex":[0.995055,0.001609436,0.000498367,0.0004476615,0.002157386,0.0002322241],"domain_scores_gemma":[0.9774327,0.00944686,0.006735276,0.001177893,0.004491852,0.0007154675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007444652,0.0003387868,0.7174202,0.0006400787,0.0003613307,0.0002559405,0.01433844,0.001941052,0.01869633,0.007309744,0.002425567,0.2355281],"study_design_scores_gemma":[0.00002570586,0.0006415847,0.9546936,0.0001117804,0.0001283712,0.0006182718,0.009283147,0.01075673,0.00849066,0.007662915,0.007451966,0.0001353422],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9543831,0.0003378367,0.01937171,0.0002982152,0.00006510548,0.0002282086,0.0006457847,0.0001788013,0.02449136],"genre_scores_gemma":[0.9912001,0.0001367545,0.006729433,0.0000512566,0.00003247756,0.0001159688,0.0004065315,0.00001876771,0.001308776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003876772,"threshold_uncertainty_score":0.02050257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156413587","doi":"10.1613/jair.4272","title":"Sentiment Analysis of Short Informal Texts","year":2014,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":890,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; SemEval; Task (project management); Lexicon; Sentiment analysis; Phrase; Natural language processing; Artificial intelligence; Variety (cybernetics); Word (group theory); Term (time); Set (abstract data type); Linguistics","authors":[{"name":"Svetlana Kiritchenko","is_ca":true},{"name":"Xiaodan Zhu","is_ca":true},{"name":"Seyed Mohammad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1410959079151924,"gpt":0.4268329994839138,"spread":0.2857370915687214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008472537,0.0008502281,0.0005542776,0.001855311,0.0003991889,0.001054762,0.0003945854,0.000349615,0.004946096],"category_scores_gemma":[0.00449419,0.0001653096,0.0005781113,0.001020459,0.0002226372,0.001014735,0.0006578276,0.0004129567,0.004366931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002938476,"about_ca_system_score_gemma":0.0003167928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006610026,"about_ca_topic_score_gemma":0.001277136,"domain_scores_codex":[0.9988631,0.0002494388,0.0001310711,0.0001997902,0.0004717226,0.00008483694],"domain_scores_gemma":[0.9974105,0.000837594,0.0003894728,0.0001982417,0.001066459,0.00009781727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007428139,0.0002456992,0.01720615,0.001535601,0.0002159345,0.0006995876,0.001047214,0.003034159,0.2145821,0.003283647,0.04082642,0.7165807],"study_design_scores_gemma":[0.0002005396,0.001285425,0.1620207,0.0005289968,0.0003904366,0.002338798,0.002571456,0.3234358,0.2359157,0.02292166,0.2481312,0.0002593223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4365283,0.003157627,0.4843453,0.001237366,0.001075216,0.001594182,0.02267822,0.01328597,0.03609788],"genre_scores_gemma":[0.7146364,0.001647339,0.2279976,0.0004047088,0.001023147,0.001029716,0.03492114,0.0007610975,0.0175788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004946096,"threshold_uncertainty_score":0.01654631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162010436","doi":"","title":"Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon","year":2010,"lang":"en","type":"article","venue":"NPARC","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":873,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Lexicon; Computer science; Natural language processing; Word (group theory); Sentiment analysis; Emotion classification; Orientation (vector space); Artificial intelligence; Term (time); Polarity (international relations); Quality (philosophy); Emotion recognition; Semantics (computer science); Speech recognition; Linguistics; Mathematics","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Peter D. Turney","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02472797718163747,"gpt":0.2964459804661465,"spread":0.271718003284509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003237154,0.0007327201,0.0004213098,0.002885029,0.001044667,0.001491177,0.0008060238,0.0008030381,0.003035499],"category_scores_gemma":[0.01413025,0.0002828419,0.0005811537,0.001975972,0.0009835534,0.001338092,0.00197082,0.0008643619,0.001876628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008646214,"about_ca_system_score_gemma":0.0006577972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260371,"about_ca_topic_score_gemma":0.004129057,"domain_scores_codex":[0.9961195,0.002109001,0.0003603739,0.0004874477,0.0007508595,0.0001728956],"domain_scores_gemma":[0.9885427,0.007054177,0.001032812,0.001043756,0.002017295,0.0003093722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003095478,0.002307815,0.1078011,0.003417228,0.0004013095,0.00441221,0.0325895,0.01717135,0.250888,0.01578622,0.09766373,0.4644661],"study_design_scores_gemma":[0.0008138227,0.001853039,0.3978388,0.0005330638,0.0003343799,0.002981341,0.02500175,0.2263395,0.09878345,0.03665164,0.2081064,0.0007627791],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8139123,0.0003511957,0.1437953,0.0008871724,0.0002460492,0.004161031,0.01502479,0.002127429,0.01949469],"genre_scores_gemma":[0.793251,0.0001736316,0.1651577,0.00058946,0.0001263223,0.007983799,0.02676162,0.0004660407,0.005490548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003237154,"threshold_uncertainty_score":0.01711994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2460159515","doi":"10.18653/v1/s16-1003","title":"SemEval-2016 Task 6: Detecting Stance in Tweets","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":857,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"SemEval; Task (project management); Computer science; Natural language processing; Artificial intelligence; Engineering","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true},{"name":"Parinaz Sobhani","is_ca":true},{"name":"Xiaodan Zhu","is_ca":true},{"name":"Colin Cherry","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01537311927603455,"gpt":0.2510792161289844,"spread":0.2357060968529498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007387589,0.004567104,0.002643278,0.003935443,0.002227932,0.00332846,0.002822154,0.005798921,0.008881683],"category_scores_gemma":[0.01814176,0.0007218961,0.002325499,0.00226506,0.0009011097,0.004902637,0.005642655,0.003055768,0.01670351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001298525,"about_ca_system_score_gemma":0.002430315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003971844,"about_ca_topic_score_gemma":0.008696359,"domain_scores_codex":[0.9919018,0.002598772,0.001012634,0.00199294,0.001772949,0.0007208758],"domain_scores_gemma":[0.9833348,0.005882501,0.001130754,0.004002733,0.003882899,0.001766299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003368624,0.001989363,0.02034142,0.00405806,0.0007174536,0.001544196,0.00130491,0.007702335,0.03239281,0.001904124,0.6530277,0.2716492],"study_design_scores_gemma":[0.001818624,0.00329644,0.05630611,0.0007769074,0.0005981102,0.004869314,0.004074328,0.2325886,0.1247306,0.01363144,0.5566594,0.0006501694],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.394786,0.005888069,0.09832889,0.005072936,0.0104479,0.004549867,0.3268563,0.1101844,0.04388577],"genre_scores_gemma":[0.2724624,0.0006359637,0.1645146,0.001247716,0.001290451,0.002076005,0.525142,0.004089105,0.02854185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008881683,"threshold_uncertainty_score":0.03906977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063596712","doi":"10.1111/j.1467-8640.2006.00277.x","title":"SENTIMENT CLASSIFICATION of MOVIE REVIEWS USING CONTEXTUAL VALENCE SHIFTERS","year":2006,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":750,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Valence (chemistry); Negation; Natural language processing; Computer science; Artificial intelligence; Term (time); Sentiment analysis; Support vector machine; Pattern recognition (psychology); Physics; Trigram","authors":[{"name":"Alistair Kennedy","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09465421034018377,"gpt":0.3375719904772647,"spread":0.2429177801370809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009841261,0.000576772,0.0007761735,0.003058126,0.0002924312,0.0008156924,0.0003181821,0.000391764,0.001297093],"category_scores_gemma":[0.003475118,0.0001635021,0.0006594615,0.001410314,0.0002290791,0.0005502528,0.0003688343,0.0004834455,0.0005932138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004058248,"about_ca_system_score_gemma":0.0002806115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001307715,"about_ca_topic_score_gemma":0.001912997,"domain_scores_codex":[0.9990803,0.0001800886,0.00009981182,0.0001864346,0.0003499235,0.0001034441],"domain_scores_gemma":[0.9978649,0.0006745898,0.0003684662,0.0001382929,0.000861726,0.00009196759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002329854,0.0004376147,0.08495704,0.0004907828,0.0005402387,0.0002888178,0.0004569872,0.01492068,0.07740962,0.001218429,0.005026393,0.8119235],"study_design_scores_gemma":[0.0001657265,0.0008941382,0.167168,0.00009387392,0.0003549221,0.0005197907,0.0004157485,0.7770928,0.04477221,0.002647023,0.005724313,0.0001514239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8923436,0.001853059,0.09623964,0.0002394598,0.0002887016,0.0003018301,0.001413095,0.001450229,0.005870309],"genre_scores_gemma":[0.9374825,0.0002730281,0.05949343,0.00005179531,0.0002003373,0.0001454026,0.001267119,0.00005221031,0.001034129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003058126,"threshold_uncertainty_score":0.005204678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2805744755","doi":"10.18653/v1/s18-1001","title":"SemEval-2018 Task 1: Affect in Tweets","year":2018,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":745,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"SemEval; Valence (chemistry); Computer science; Affect (linguistics); Task (project management); Natural language processing; Sentiment analysis; Emotion detection; Artificial intelligence; Emotion classification; Focus (optics); Emotion recognition; Linguistics","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Felipe Bravo-Márquez","is_ca":false},{"name":"Mohammad Salameh","is_ca":false},{"name":"Svetlana Kiritchenko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02371668830788393,"gpt":0.2892998895742772,"spread":0.2655832012663933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002878399,0.002798306,0.0013521,0.001620739,0.001627718,0.002428146,0.001675331,0.002509139,0.01580268],"category_scores_gemma":[0.01103201,0.0004696585,0.001133847,0.001313416,0.0006195318,0.002618249,0.003330902,0.00221923,0.01859864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009584567,"about_ca_system_score_gemma":0.001076362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004057583,"about_ca_topic_score_gemma":0.006869556,"domain_scores_codex":[0.9971797,0.001037437,0.0002148236,0.0006613045,0.0006197965,0.0002869382],"domain_scores_gemma":[0.9945962,0.002414799,0.0003562726,0.001048416,0.001142792,0.0004414514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003128348,0.001788766,0.0237293,0.002507167,0.0002577816,0.000666461,0.001672568,0.006993699,0.01945646,0.002447283,0.7487391,0.1886131],"study_design_scores_gemma":[0.001371591,0.002174537,0.1174227,0.0006429255,0.0003174327,0.002101234,0.003739432,0.152778,0.08198225,0.01205259,0.6248644,0.0005530199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.3836173,0.003147303,0.055097,0.003134677,0.003370913,0.004544154,0.4549326,0.04828475,0.04387127],"genre_scores_gemma":[0.2869075,0.0005222962,0.08760968,0.0009721423,0.0009413367,0.007057306,0.5863435,0.003176804,0.02646946],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01580268,"threshold_uncertainty_score":0.05286521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2252057809","doi":"10.3115/v1/s14-2076","title":"NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews","year":2014,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":709,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Sentiment analysis; Computer science; Data science; Information retrieval; Natural language processing","authors":[{"name":"Svetlana Kiritchenko","is_ca":false},{"name":"Xiaodan Zhu","is_ca":false},{"name":"Colin Cherry","is_ca":false},{"name":"Saif M. Mohammad","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01415576873543839,"gpt":0.2401774215005479,"spread":0.2260216527651095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003536773,0.003026963,0.001606505,0.004270817,0.002127359,0.003981858,0.002242172,0.002500417,0.004695818],"category_scores_gemma":[0.01393342,0.0008098276,0.001153728,0.003609419,0.0007488593,0.00191083,0.001868899,0.002064424,0.005079177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005323591,"about_ca_system_score_gemma":0.01122582,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4546265,"about_ca_topic_score_gemma":0.6655841,"domain_scores_codex":[0.9957733,0.0009586558,0.0002533856,0.0007716324,0.001821681,0.0004213677],"domain_scores_gemma":[0.9889686,0.001503795,0.0003586547,0.0008910807,0.007201266,0.001076586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001118547,0.000666943,0.02700036,0.001390457,0.0006286369,0.0006367431,0.0009957199,0.002509373,0.01772739,0.001459008,0.7739741,0.1718927],"study_design_scores_gemma":[0.001065998,0.00106536,0.2296575,0.0005602734,0.0006173124,0.001570084,0.003860732,0.1735165,0.03414017,0.003571359,0.5498543,0.0005203648],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3943127,0.01374359,0.09091078,0.009736367,0.00623482,0.005414748,0.3813159,0.05001418,0.04831687],"genre_scores_gemma":[0.2051328,0.002222277,0.1536907,0.001381523,0.0006996011,0.00113258,0.5669489,0.00288809,0.06590348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5453735,"threshold_uncertainty_score":0.9039606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2618843390","doi":"10.1145/3057270","title":"Current State of Text Sentiment Analysis from Opinion to Emotion Mining","year":2017,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":485,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Sentiment analysis; Computer science; Perspective (graphical); Emotion classification; Focus (optics); Data science; Emotion detection; Concept mining; Natural language processing; Artificial intelligence; Web mining; Emotion recognition; World Wide Web","authors":[{"name":"Ali Yadollahi","is_ca":true},{"name":"Ameneh Gholipour Shahraki","is_ca":true},{"name":"Osmar R. Zai͏̈ane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1454330033349877,"gpt":0.4061492283394427,"spread":0.2607162250044549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003720121,0.001075376,0.001540365,0.004443833,0.0006292531,0.003170929,0.001739252,0.001148357,0.005874215],"category_scores_gemma":[0.01028395,0.0004611436,0.001367462,0.006268319,0.000995111,0.004834578,0.001153019,0.001777782,0.004898807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005538,"about_ca_system_score_gemma":0.001596213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001709978,"about_ca_topic_score_gemma":0.001356893,"domain_scores_codex":[0.9982947,0.0004969021,0.0001828124,0.0003232069,0.0006135057,0.00008899564],"domain_scores_gemma":[0.9915192,0.005054228,0.0003980843,0.0002910445,0.002602202,0.0001351931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005445055,0.00005589549,0.0009573728,0.006002518,0.0000817309,0.00004070223,0.0002698145,0.0003162901,0.000889482,0.008227047,0.04321614,0.9398886],"study_design_scores_gemma":[0.00004827234,0.0001238176,0.006502678,0.007208796,0.0003366232,0.0005826642,0.001048864,0.006513797,0.002707596,0.03639426,0.9384437,0.00008898725],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005580452,0.8879783,0.06028921,0.0106113,0.003140445,0.0003201775,0.0009007183,0.0008013382,0.03037803],"genre_scores_gemma":[0.02997253,0.9082668,0.04219885,0.003565154,0.005561953,0.0004612739,0.001785275,0.0002594577,0.007928682],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005874215,"threshold_uncertainty_score":0.01967412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1589554437","doi":"10.48550/arxiv.1308.6242","title":"NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Lexicon; Sentiment analysis; Task (project management); Word (group theory); Variety (cybernetics); Natural language processing; Term (time); Artificial intelligence; State (computer science); Information retrieval; Linguistics","authors":[{"name":"Saif M. Mohammad","is_ca":false},{"name":"Svetlana Kiritchenko","is_ca":false},{"name":"Xiaodan Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02929141363701235,"gpt":0.1701409945858029,"spread":0.1408495809487905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007571367,0.002286258,0.001488346,0.006824818,0.003224473,0.003920916,0.003286567,0.001434833,0.01315561],"category_scores_gemma":[0.01567723,0.001161536,0.001787228,0.0042533,0.00112736,0.004669303,0.003551071,0.002756419,0.01464532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008288885,"about_ca_system_score_gemma":0.02250096,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.7050651,"about_ca_topic_score_gemma":0.7127748,"domain_scores_codex":[0.9939033,0.001130539,0.0002796713,0.001176082,0.002938432,0.0005718694],"domain_scores_gemma":[0.9860761,0.001527004,0.0002833704,0.001320429,0.009995261,0.0007979293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007349603,0.000327977,0.01383351,0.0009111307,0.0003071688,0.000231171,0.001063514,0.005959657,0.02665848,0.006746707,0.2567023,0.6865234],"study_design_scores_gemma":[0.0003673373,0.0004240167,0.02543899,0.0006278061,0.0004246709,0.0002984308,0.002270771,0.4438404,0.04699035,0.01183543,0.4670581,0.0004236014],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0783383,0.01028157,0.5904223,0.007668769,0.002614113,0.00347652,0.06057868,0.1624863,0.08413352],"genre_scores_gemma":[0.1501369,0.004005422,0.7076055,0.001449909,0.000390358,0.001345284,0.08338673,0.009496625,0.04218323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7050651,"threshold_uncertainty_score":0.5933437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2347127863","doi":"10.1145/3003433","title":"Stance and Sentiment in Tweets","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":435,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Computer science; Task (project management); SemEval; Sentiment analysis; Natural language processing; Artificial intelligence; Word (group theory); Simple (philosophy); Test (biology); Linguistics","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Parinaz Sobhani","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02073649958369465,"gpt":0.2862651887421067,"spread":0.265528689158412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000747997,0.0005969935,0.000365776,0.00238276,0.0007061919,0.001295915,0.0002771539,0.000748096,0.003340525],"category_scores_gemma":[0.006165423,0.0001804721,0.0003450439,0.002166611,0.000321216,0.001836967,0.001079507,0.0006973692,0.002957773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004825799,"about_ca_system_score_gemma":0.0003223185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001946138,"about_ca_topic_score_gemma":0.004130666,"domain_scores_codex":[0.998757,0.0003017587,0.0001636274,0.0002704782,0.0003910172,0.0001162253],"domain_scores_gemma":[0.9968523,0.001112884,0.0007463368,0.0002765345,0.0007690667,0.0002428604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003267922,0.000428152,0.3475066,0.002862473,0.0002964042,0.002138303,0.01025609,0.003958648,0.1303635,0.01074724,0.1187037,0.369471],"study_design_scores_gemma":[0.0001254887,0.0006466849,0.5770314,0.0006668693,0.0002282049,0.002633197,0.009225561,0.07009761,0.05336012,0.01977903,0.2659627,0.0002429921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8306924,0.002316444,0.03555588,0.001661388,0.001083971,0.0003885931,0.09106079,0.001549817,0.0356908],"genre_scores_gemma":[0.8945733,0.0008108951,0.02743742,0.0003274026,0.0004707797,0.0003349413,0.06565226,0.0002234347,0.01016953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003340525,"threshold_uncertainty_score":0.01117516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970748008","doi":"10.18653/v1/d19-1569","title":"Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree","year":2019,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":427,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Dependency (UML); Computer science; Convolution (computer science); Natural language processing; Tree (set theory); Zhàng; Artificial intelligence; Joint (building); Sentiment analysis; China; Mathematics; Engineering; Geography; Archaeology; Artificial neural network; Combinatorics; Architectural engineering","authors":[{"name":"Kai Sun","is_ca":true},{"name":"Richong Zhang","is_ca":true},{"name":"Samuel Mensah","is_ca":true},{"name":"Yongyi Mao","is_ca":true},{"name":"Xudong Liu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0186012261346731,"gpt":0.2538771018828641,"spread":0.2352758757481909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006321848,0.0004722085,0.0005765244,0.001215728,0.0004000731,0.0007310417,0.0005657026,0.0003769453,0.002959037],"category_scores_gemma":[0.001543789,0.0002569582,0.0008219061,0.00165262,0.0001841914,0.001259429,0.0007510339,0.0006385801,0.001420529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003686506,"about_ca_system_score_gemma":0.0006333228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003949378,"about_ca_topic_score_gemma":0.007022544,"domain_scores_codex":[0.9996977,0.0000657165,0.00002101427,0.0000643481,0.00009546497,0.00005579308],"domain_scores_gemma":[0.9994904,0.0001775057,0.00005077628,0.00006471707,0.0001838682,0.00003272897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004328566,0.0001895919,0.007112656,0.0001668381,0.0002050035,0.0003051431,0.0001960674,0.04356689,0.04026283,0.01504163,0.01977334,0.8727471],"study_design_scores_gemma":[0.000008583449,0.00003952041,0.001753651,0.000007638057,0.00003686631,0.00007973716,0.00003140737,0.9804427,0.004953475,0.009475437,0.003159836,0.00001100993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05699981,0.0006325947,0.9327896,0.0002215266,0.0001261301,0.00007458921,0.0008375972,0.004437428,0.003880673],"genre_scores_gemma":[0.6314942,0.0007021733,0.3578725,0.0001624434,0.0001380445,0.0001311479,0.003683438,0.0005356771,0.005280453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003949378,"threshold_uncertainty_score":0.009898961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949709688","doi":"10.48550/arxiv.1308.6242","title":"NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of\\n Tweets","year":2013,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":419,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Lexicon; Sentiment analysis; Task (project management); Computer science; Variety (cybernetics); Word (group theory); Natural language processing; Artificial intelligence; Term (time); State (computer science); Information retrieval; Linguistics; Engineering","authors":[{"name":"Saif M. Mohammad","is_ca":false},{"name":"Svetlana Kiritchenko","is_ca":false},{"name":"Xiaodan Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04688768530605174,"gpt":0.1887853829841318,"spread":0.14189769767808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005543008,0.002712264,0.001533464,0.005633285,0.002948772,0.003270858,0.003218183,0.00150024,0.01279726],"category_scores_gemma":[0.01235011,0.001084565,0.001980444,0.003310693,0.000995883,0.004178568,0.003078223,0.002927518,0.01437589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006142495,"about_ca_system_score_gemma":0.01342696,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.5547163,"about_ca_topic_score_gemma":0.5817537,"domain_scores_codex":[0.9950963,0.0008508728,0.0002354711,0.001126128,0.002215538,0.0004756438],"domain_scores_gemma":[0.9908857,0.001150928,0.0002035138,0.001020797,0.006210127,0.000529015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000717985,0.0003926424,0.01030174,0.0007967275,0.000345378,0.0002267117,0.0006817837,0.006555546,0.03332411,0.005219121,0.2324078,0.7090305],"study_design_scores_gemma":[0.0003473276,0.000399419,0.01887206,0.0003765858,0.0003408143,0.0002656811,0.001253893,0.6107902,0.05060615,0.008643638,0.3078192,0.0002851814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0840175,0.009291767,0.6160948,0.005566546,0.002646114,0.003084517,0.05144837,0.1636321,0.06421845],"genre_scores_gemma":[0.1631461,0.003171447,0.6821747,0.00156092,0.0004469398,0.001282266,0.09977223,0.007935128,0.04051038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5547163,"threshold_uncertainty_score":0.8958122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569507287","doi":"10.1111/coin.12024","title":"Using Hashtags to Capture Fine Emotion Categories from Tweets","year":2014,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":412,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Lexicon; Social media; Computer science; Emotion classification; Sentiment analysis; Big Five personality traits; Word (group theory); Microblogging; Admiration; Natural language processing; Artificial intelligence; Emotion detection; Personality; Psychology; Emotion recognition; Linguistics; Social psychology; World Wide Web","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06287620001503862,"gpt":0.3180379788060219,"spread":0.2551617787909832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007576214,0.0006389436,0.0002707421,0.00359472,0.0004275644,0.0008780014,0.0002291846,0.0004849207,0.001794761],"category_scores_gemma":[0.004611471,0.0002151795,0.0003035522,0.002511237,0.0003621774,0.001884383,0.0007454214,0.0005860234,0.001698189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003258093,"about_ca_system_score_gemma":0.0002078809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001519383,"about_ca_topic_score_gemma":0.004796027,"domain_scores_codex":[0.9992689,0.0001706232,0.0001117127,0.0001850176,0.0001913555,0.00007235756],"domain_scores_gemma":[0.9950537,0.00230672,0.001048596,0.0005171642,0.0008877413,0.0001860312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001714114,0.00041845,0.2406935,0.001635342,0.0002337725,0.0008175884,0.006979169,0.004307527,0.1830636,0.00533133,0.02199209,0.5328134],"study_design_scores_gemma":[0.0001174213,0.0009422607,0.6785395,0.0002345719,0.000264908,0.001334799,0.005727293,0.1304507,0.08696342,0.02086444,0.07429033,0.0002704749],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8168144,0.0009187575,0.1412355,0.0004796403,0.000558344,0.0008311642,0.02461309,0.003066441,0.01148269],"genre_scores_gemma":[0.888793,0.0003905009,0.08808088,0.0001961466,0.0002523765,0.000588224,0.01650218,0.0002182558,0.004978335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00359472,"threshold_uncertainty_score":0.006004035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1822239915","doi":"10.1146/annurev-linguistics-011415-040518","title":"Sentiment Analysis: An Overview from Linguistics","year":2015,"lang":"en","type":"article","venue":"Annual Review of Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":402,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Sentiment analysis; Computer science; Natural language processing; Context (archaeology); Field (mathematics); Intersection (aeronautics); Computational linguistics; Linguistics; Social media; Repertoire; Corpus linguistics; Artificial intelligence; Linguistic analysis; World Wide Web; History","authors":[{"name":"Maite Taboada","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08045031633417499,"gpt":0.3777416211088148,"spread":0.2972913047746398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003230198,0.001709997,0.001854393,0.009020203,0.001260016,0.004892177,0.001423686,0.002413373,0.003585845],"category_scores_gemma":[0.004866475,0.0008630374,0.001334734,0.00887838,0.002229943,0.008028846,0.002095318,0.00310371,0.004297051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952788,"about_ca_system_score_gemma":0.002143303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001702411,"about_ca_topic_score_gemma":0.001591805,"domain_scores_codex":[0.9979168,0.0006102748,0.0002850646,0.0003165042,0.0007757014,0.00009569854],"domain_scores_gemma":[0.9965981,0.002214825,0.0001906976,0.0001023902,0.0007849353,0.000109159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006313447,0.00008031613,0.001464179,0.009120155,0.0001255356,0.0003586416,0.001260919,0.0007284555,0.00220344,0.04139165,0.073952,0.8692515],"study_design_scores_gemma":[0.0000182593,0.00007989586,0.002688751,0.005012071,0.00008606716,0.0009284847,0.001022907,0.001986302,0.0009050295,0.08253077,0.9046589,0.00008263014],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001716939,0.9302893,0.03569873,0.007920843,0.002415478,0.0001757339,0.0002639352,0.0003320351,0.02118703],"genre_scores_gemma":[0.01167208,0.946485,0.0294238,0.002584467,0.004666857,0.0002839797,0.0004560665,0.0001541061,0.00427351],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.009020203,"threshold_uncertainty_score":0.01708311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027304069","doi":"10.1016/b978-0-08-100508-8.00009-6","title":"Sentiment Analysis","year":2016,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":384,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sentiment analysis; Paralanguage; Computer science; Natural language processing; Task (project management); Valence (chemistry); Artificial intelligence; Tone (literature); Linguistics; Psychology; Communication","authors":[{"name":"Saif M. Mohammad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01704855522383952,"gpt":0.2469778397429098,"spread":0.2299292845190702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001048445,0.001058687,0.0005399038,0.002981645,0.0008545935,0.003016263,0.0006405941,0.0005324837,0.08230919],"category_scores_gemma":[0.002855597,0.0003631955,0.0009275259,0.002597005,0.0002722704,0.001933297,0.001215863,0.0009557155,0.06671877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000529505,"about_ca_system_score_gemma":0.0008054068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001105908,"about_ca_topic_score_gemma":0.001812971,"domain_scores_codex":[0.9992567,0.00009924451,0.0000584787,0.000150592,0.0003802055,0.00005471485],"domain_scores_gemma":[0.9993321,0.0001287266,0.00004080487,0.0001031993,0.0003637564,0.00003130934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004211648,0.0000464102,0.0007198282,0.0002554778,0.00003892479,0.00006327283,0.0001848816,0.0004570999,0.009999689,0.01118105,0.2107876,0.7662237],"study_design_scores_gemma":[0.00002152666,0.00004423552,0.004556004,0.0002549925,0.00008061686,0.000478574,0.000350683,0.01354572,0.01546715,0.02343174,0.9417278,0.00004104259],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01328876,0.003694419,0.3219801,0.002882465,0.002617283,0.0008172875,0.01430111,0.01441942,0.6259991],"genre_scores_gemma":[0.08286243,0.005019545,0.2419802,0.001295581,0.001203435,0.0008537626,0.03488626,0.003991609,0.6279072],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.08230919,"threshold_uncertainty_score":0.2753516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2741447225","doi":"10.18653/v1/p17-1067","title":"EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":383,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Task (project management); Emotion detection; Emotion recognition; Deep neural networks; Artificial intelligence; Ranging; Deep learning; Emotion classification; Artificial neural network; Task analysis; Machine learning; Natural language processing","authors":[{"name":"Muhammad Abdul-Mageed","is_ca":true},{"name":"Lyle Ungar","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02179387651304163,"gpt":0.2557212958222981,"spread":0.2339274193092565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005769435,0.001341719,0.0005258371,0.0005067598,0.0002532269,0.0006128405,0.001038027,0.0006693887,0.002669726],"category_scores_gemma":[0.001397465,0.0003398071,0.0005686859,0.0003281635,0.0002075989,0.001128636,0.0007793367,0.001132499,0.001723391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000473559,"about_ca_system_score_gemma":0.0004401688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004378988,"about_ca_topic_score_gemma":0.009376587,"domain_scores_codex":[0.9997461,0.00005383235,0.00001234944,0.00009185837,0.00004674673,0.00004905129],"domain_scores_gemma":[0.9997216,0.00009390322,0.00003347125,0.00005265349,0.00007407508,0.00002418721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008860066,0.0009573024,0.0122878,0.0003571151,0.0004998458,0.0003678387,0.000233997,0.135453,0.08620799,0.007470899,0.08199541,0.6732829],"study_design_scores_gemma":[0.00003488647,0.0001318766,0.002290682,0.00002025945,0.00004408251,0.00004808584,0.00002698761,0.9764227,0.01183067,0.004059944,0.005067677,0.00002219517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2349489,0.002621684,0.715647,0.0009944519,0.0008486332,0.0002822373,0.005961481,0.0276881,0.01100753],"genre_scores_gemma":[0.751632,0.0007114587,0.2146734,0.0006983256,0.0001904481,0.0003606385,0.01473096,0.0006944094,0.0163084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004378988,"threshold_uncertainty_score":0.0089311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035119815","doi":"10.1109/jbhi.2020.3001216","title":"Deep Sentiment Classification and Topic Discovery on Novel Coronavirus or COVID-19 Online Discussions: NLP Using LSTM Recurrent Neural Network Approach","year":2020,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":379,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Social Science Fund of China; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Nanjing Science and Technology Commission; National Science Foundation","keywords":"Computer science; Artificial intelligence; Sentiment analysis; Social media; Recurrent neural network; Coronavirus disease 2019 (COVID-19); Natural language processing; Deep learning; Machine learning; Artificial neural network; Public health; Decision tree; The Internet; Support vector machine; World Wide Web; Medicine; Disease","authors":[{"name":"Hamed Jelodar","is_ca":false},{"name":"Yongli Wang","is_ca":false},{"name":"Rita Orji","is_ca":true},{"name":"Shucheng Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2666507334657404,"gpt":0.4049349140857755,"spread":0.1382841806200351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009390738,0.0007558315,0.0004056606,0.001184194,0.0004246781,0.000688549,0.0004981231,0.0006485231,0.00133839],"category_scores_gemma":[0.002076603,0.0001945182,0.0008300885,0.0006675969,0.0002147004,0.00101152,0.0004888964,0.0009570431,0.0006181799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006600278,"about_ca_system_score_gemma":0.0004884574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004417604,"about_ca_topic_score_gemma":0.005256646,"domain_scores_codex":[0.9995825,0.0001339562,0.0000294661,0.0001040625,0.00005989763,0.00009011727],"domain_scores_gemma":[0.9990569,0.0004928464,0.0001341514,0.0000355251,0.0002409731,0.00003969295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00115199,0.001167245,0.04060876,0.0004661286,0.0003724224,0.0009550811,0.002119079,0.09973584,0.06457489,0.005728298,0.01747351,0.7656468],"study_design_scores_gemma":[0.00001016796,0.00005352331,0.003164538,0.00001026964,0.00003889791,0.00002344201,0.0001748432,0.9900587,0.003833748,0.001684684,0.0009383533,0.000008897466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6692168,0.001092162,0.3165554,0.002060718,0.0003963042,0.0002163286,0.001458169,0.001562696,0.00744142],"genre_scores_gemma":[0.9538018,0.000310897,0.03971899,0.0001572151,0.0002461542,0.00009358583,0.001753962,0.0000460259,0.003871416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004417604,"threshold_uncertainty_score":0.008783758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2467186984","doi":"10.18653/v1/s15-2078","title":"SemEval-2015 Task 10: Sentiment Analysis in Twitter","year":2015,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":367,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"SemEval; Sentiment analysis; Computer science; Task (project management); Context (archaeology); Phrase; Polarity (international relations); Natural language processing; Set (abstract data type); Artificial intelligence; History","authors":[{"name":"Sara Rosenthal","is_ca":true},{"name":"Preslav Nakov","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true},{"name":"Saif M. Mohammad","is_ca":true},{"name":"Alan Ritter","is_ca":true},{"name":"Veselin Stoyanov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04611232732077405,"gpt":0.3102190803927146,"spread":0.2641067530719405,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005385806,0.004058355,0.001585819,0.002563649,0.002272058,0.003035622,0.002199928,0.002942943,0.01138386],"category_scores_gemma":[0.01404767,0.0005384907,0.002286937,0.001874299,0.0006723032,0.004020576,0.004572946,0.002807454,0.01427697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001704293,"about_ca_system_score_gemma":0.002342082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006315813,"about_ca_topic_score_gemma":0.02087009,"domain_scores_codex":[0.995087,0.002174644,0.0003833684,0.0009882402,0.0008520276,0.0005147053],"domain_scores_gemma":[0.9941889,0.002692089,0.0003533454,0.0008882301,0.001259213,0.0006182275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001427455,0.001077739,0.0114847,0.001693986,0.0004622545,0.0006474751,0.0009966214,0.004879272,0.01642088,0.00252211,0.746649,0.2117383],"study_design_scores_gemma":[0.001173929,0.001871263,0.04882609,0.0005437852,0.0004265097,0.001697859,0.003642272,0.2289357,0.05319828,0.01880262,0.6404085,0.0004731986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3299616,0.008051025,0.1846885,0.00819768,0.01012148,0.006105721,0.3019909,0.08519627,0.06568688],"genre_scores_gemma":[0.2739925,0.0009990304,0.2200867,0.002443251,0.001499306,0.004511158,0.4569819,0.004524003,0.03496218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01138386,"threshold_uncertainty_score":0.03808284,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964325543","doi":"10.18653/v1/d16-1057","title":"Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":359,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Army Research Office; National Institute of Biomedical Imaging and Bioengineering; Multidisciplinary University Research Initiative; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"WordNet; Computer science; Sentiment analysis; Domain (mathematical analysis); Artificial intelligence; Natural language processing; Social media; Word (group theory); Linguistics; World Wide Web; Mathematics","authors":[{"name":"William L. Hamilton","is_ca":false},{"name":"Kevin B. Clark","is_ca":false},{"name":"Jure Leskovec","is_ca":false},{"name":"Dan Jurafsky","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02815432780206759,"gpt":0.2362522130469846,"spread":0.208097885244917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00188847,0.001181158,0.0005097077,0.002947717,0.0007523775,0.001109671,0.000711307,0.0007095165,0.001990952],"category_scores_gemma":[0.007811815,0.0006242908,0.0008379291,0.001871446,0.0007296243,0.002027305,0.001567525,0.001006239,0.001897544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007167247,"about_ca_system_score_gemma":0.001132959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00217142,"about_ca_topic_score_gemma":0.007714901,"domain_scores_codex":[0.9988721,0.0004293263,0.0001008359,0.0003226773,0.0002050745,0.00006995883],"domain_scores_gemma":[0.995593,0.002171595,0.0004097875,0.0006359236,0.001051184,0.0001384926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006597337,0.001328751,0.04461469,0.00196502,0.0004520234,0.001219471,0.002265065,0.06306192,0.1476763,0.02039478,0.08751326,0.6288489],"study_design_scores_gemma":[0.0003026853,0.0005824793,0.03097151,0.0002985217,0.0002580094,0.0009298065,0.001740202,0.7542147,0.0761065,0.03912318,0.09528698,0.0001855048],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4129568,0.0008984933,0.5284621,0.0008606784,0.0004106878,0.001261611,0.01930768,0.007604753,0.02823713],"genre_scores_gemma":[0.5671452,0.0007185321,0.3570312,0.0004307079,0.0001750517,0.001779437,0.0657922,0.0009348186,0.005992766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002947717,"threshold_uncertainty_score":0.009987295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116401198","doi":"10.1109/icdm.2008.94","title":"Modeling and Predicting the Helpfulness of Online Reviews","year":2008,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":324,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Helpfulness; Computer science; Quality (philosophy); Data science; Resource (disambiguation); Psychology","authors":[{"name":"Yang Liu","is_ca":true},{"name":"Aijun An","is_ca":true},{"name":"Xiaohui Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07223397040685091,"gpt":0.2871824448989911,"spread":0.2149484744921402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003213453,0.0007500395,0.000666492,0.001939242,0.0002372665,0.0009739682,0.0006117984,0.0009172987,0.0004546746],"category_scores_gemma":[0.01692199,0.000337374,0.0004296442,0.001103655,0.0002654742,0.001097332,0.0003022478,0.0008639403,0.0003351561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005552065,"about_ca_system_score_gemma":0.0005060828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004380575,"about_ca_topic_score_gemma":0.005634597,"domain_scores_codex":[0.9989361,0.0004690886,0.00009585953,0.0002002361,0.0002258213,0.00007290015],"domain_scores_gemma":[0.9834932,0.01192743,0.002320018,0.0003406134,0.00170598,0.0002128167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005476446,0.0005983574,0.1701107,0.000440961,0.0003207873,0.0005893371,0.0005885593,0.5670464,0.01005821,0.004783338,0.005795208,0.2391204],"study_design_scores_gemma":[0.000005137541,0.00003329973,0.005818525,0.000005511099,0.00001456511,0.00004087247,0.00001875283,0.9925048,0.0005070496,0.0008208621,0.0002239574,0.000006655971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8237115,0.00144881,0.1704749,0.001026744,0.00006585193,0.0001541791,0.0007906698,0.0005086103,0.001818746],"genre_scores_gemma":[0.9636944,0.0004638499,0.03381705,0.00004778427,0.0001435031,0.00007304516,0.0006436737,0.00002501033,0.001091685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004380575,"threshold_uncertainty_score":0.01699454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983286042","doi":"10.1145/1277741.1277845","title":"ARSA","year":2007,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":309,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Probabilistic latent semantic analysis; Computer science; Popularity; Sentiment analysis; Product (mathematics); Information retrieval; Feature selection; Topic model; Selection (genetic algorithm); Artificial intelligence; Data science; Psychology","authors":[{"name":"Yang Liu","is_ca":true},{"name":"Aijun An","is_ca":true},{"name":"Xiaohui Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0136783936592515,"gpt":0.2656939327420778,"spread":0.2520155390828263,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001889309,0.001315866,0.0008561303,0.001333949,0.0007332014,0.002798394,0.002591504,0.001496357,0.08071102],"category_scores_gemma":[0.006210824,0.0004829984,0.001852167,0.001428078,0.0004117913,0.002774574,0.001927411,0.001125454,0.08275122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006479726,"about_ca_system_score_gemma":0.001376384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002145275,"about_ca_topic_score_gemma":0.002184969,"domain_scores_codex":[0.9980156,0.0004636472,0.0001636507,0.0004916039,0.000685017,0.0001803633],"domain_scores_gemma":[0.9974451,0.0005111946,0.0001783923,0.0009339354,0.0008326048,0.00009884735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005838735,0.0004038454,0.003309297,0.0007845119,0.0001597639,0.00030805,0.0002811064,0.0310559,0.007630882,0.06408467,0.2008951,0.6905029],"study_design_scores_gemma":[0.0001637306,0.0003736178,0.001584719,0.0001888318,0.0001201476,0.0006911601,0.0002384964,0.1913542,0.009012527,0.04094924,0.7552339,0.00008932738],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.01939404,0.00199792,0.6767505,0.001906796,0.001775398,0.0009921727,0.01290486,0.06074892,0.2235293],"genre_scores_gemma":[0.2252822,0.002733557,0.4786458,0.001932394,0.0008373207,0.001388941,0.04463604,0.005413741,0.23913],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.919289,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2294703018","doi":"","title":"Emotional Tweets","year":2012,"lang":"en","type":"article","venue":"Joint Conference on Lexical and Computational Semantics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":300,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"WordNet; Lexicon; Microblogging; Computer science; Social media; Natural language processing; Artificial intelligence; Task (project management); Sentiment analysis; Affect (linguistics); Emotion detection; Emotion classification; Word (group theory); Domain (mathematical analysis); Semantics (computer science); Emotion recognition; World Wide Web; Psychology; Linguistics","authors":[{"name":"Saif M. Mohammad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07082908098884917,"gpt":0.2884091368977245,"spread":0.2175800559088754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005792208,0.0005612195,0.0002389667,0.001816807,0.0008214273,0.001465918,0.0002781365,0.0005042073,0.01880561],"category_scores_gemma":[0.004555357,0.0002049193,0.0003085039,0.00137303,0.0002287517,0.001277873,0.0009358565,0.0005779634,0.01068118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004692265,"about_ca_system_score_gemma":0.0003023994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009989315,"about_ca_topic_score_gemma":0.002156689,"domain_scores_codex":[0.9991916,0.0001951983,0.00008602962,0.0001489954,0.0002819942,0.00009628008],"domain_scores_gemma":[0.9982334,0.0006509696,0.000219387,0.0001601953,0.0006394328,0.00009661433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001586394,0.0004229995,0.06185696,0.002015033,0.0001655014,0.0009325517,0.005013545,0.002713206,0.07738584,0.02024458,0.2827476,0.5449159],"study_design_scores_gemma":[0.00009291748,0.0004433505,0.1332297,0.0003586912,0.0002503645,0.001280407,0.005972221,0.02760622,0.05934488,0.01799994,0.753235,0.0001862865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3999804,0.002077863,0.1056467,0.00560809,0.004336209,0.002968382,0.1379278,0.007328215,0.3341264],"genre_scores_gemma":[0.7764744,0.001442415,0.05324656,0.001667235,0.001351506,0.002111932,0.07527221,0.0008054509,0.08762823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01880561,"threshold_uncertainty_score":0.06291109,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970431814","doi":"10.18653/v1/d19-1016","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","year":2019,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":294,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Research (Canada)","funders":"Nanyang Technological University; National Research Foundation","keywords":"Transformer; Computer science; Emotion detection; Natural language processing; Artificial intelligence; Emotion recognition; Electrical engineering; Engineering; Voltage","authors":[{"name":"Peixiang Zhong","is_ca":true},{"name":"Di Wang","is_ca":true},{"name":"Chunyan Miao","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01972994354918485,"gpt":0.2737241214849261,"spread":0.2539941779357413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006905859,0.0007155116,0.0005842981,0.002084482,0.0004754281,0.0009038282,0.0008622392,0.0005758426,0.005707395],"category_scores_gemma":[0.002359912,0.0002369251,0.0006907175,0.001469075,0.0002853315,0.002183338,0.001447782,0.0006201007,0.003659344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004955723,"about_ca_system_score_gemma":0.0006215101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002918074,"about_ca_topic_score_gemma":0.00388013,"domain_scores_codex":[0.999302,0.0001806133,0.0000493596,0.0002467029,0.0001265193,0.00009484353],"domain_scores_gemma":[0.999178,0.0003456798,0.00006338369,0.0001282311,0.0002300539,0.00005466632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001540819,0.0004503247,0.004777148,0.0005050823,0.0001626779,0.0006983275,0.0007214379,0.005916032,0.079617,0.008966409,0.02297962,0.873665],"study_design_scores_gemma":[0.00007790632,0.0003239487,0.007826638,0.00008023405,0.000281425,0.0008278265,0.001014898,0.8615488,0.07168033,0.03231062,0.02394604,0.00008127643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07070296,0.001136553,0.8934638,0.0004279976,0.0002440732,0.0003372086,0.005669303,0.01992638,0.008091799],"genre_scores_gemma":[0.7085019,0.0006064005,0.270462,0.0002375445,0.000136934,0.0003388957,0.0122208,0.0004864688,0.007009086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005707395,"threshold_uncertainty_score":0.0190931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3040884840","doi":"10.1057/s41599-020-0523-3","title":"Sentiments and emotions evoked by news headlines of coronavirus disease (COVID-19) outbreak","year":2020,"lang":"en","type":"article","venue":"Humanities and Social Sciences Communications","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Sadness; Anger; Coronavirus disease 2019 (COVID-19); Psychology; Sentence; Sentiment analysis; Coronavirus; News media; Social psychology; Disease; Medicine; Linguistics; Sociology; Media studies; Infectious disease (medical specialty); Computer science","authors":[{"name":"Faheem Aslam","is_ca":false},{"name":"Tahir Mumtaz Awan","is_ca":false},{"name":"Jabir Hussain Syed","is_ca":false},{"name":"Aisha Kashif","is_ca":false},{"name":"Mahwish Parveen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3228928790328312,"gpt":0.3940778547602795,"spread":0.07118497572744825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006061578,0.0003059898,0.0002100825,0.001716366,0.0003541067,0.0008877326,0.00008323671,0.0002401963,0.001659453],"category_scores_gemma":[0.003490197,0.00005858785,0.0002496018,0.00126826,0.0001952178,0.0004011486,0.000350134,0.0002543549,0.0004329878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003139347,"about_ca_system_score_gemma":0.0001518996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001834205,"about_ca_topic_score_gemma":0.00279491,"domain_scores_codex":[0.9995843,0.0001165693,0.00005985764,0.00005569681,0.0001320337,0.00005165985],"domain_scores_gemma":[0.9968746,0.0015284,0.0008081304,0.0000554788,0.0006059969,0.0001274548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003502062,0.0003347394,0.7289166,0.003134385,0.0004432093,0.001897209,0.01312661,0.001358227,0.05707045,0.0006622334,0.02755173,0.1620025],"study_design_scores_gemma":[0.0000174739,0.0002459561,0.9763411,0.0001456212,0.0001394937,0.0003634666,0.006601205,0.003072431,0.004384957,0.0001263611,0.008531737,0.0000301476],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908562,0.0004047377,0.0006974991,0.0001725766,0.0001002779,0.00007140163,0.00430177,0.00004115568,0.003354511],"genre_scores_gemma":[0.990491,0.0004580507,0.001638259,0.00008863914,0.0001859469,0.00009154587,0.005528924,0.0000162676,0.001501352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001834205,"threshold_uncertainty_score":0.005551398,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2606902231","doi":"10.1177/0165551517703514","title":"Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons","year":2017,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":267,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Nanyang Technological University","keywords":"Lexicon; Sentiment analysis; Computer science; Sentence; Natural language processing; Artificial intelligence; Word (group theory); Product (mathematics); Linguistics; Mathematics","authors":[{"name":"Christopher S. G. Khoo","is_ca":false},{"name":"Sathik Basha Johnkhan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09062241115274372,"gpt":0.3905624171277131,"spread":0.2999400059749694,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005324058,0.001237005,0.001137181,0.009666724,0.0007351054,0.003040866,0.0009286326,0.0006309821,0.003210828],"category_scores_gemma":[0.02076251,0.0003179307,0.001332059,0.004973399,0.0004705698,0.003719322,0.001786495,0.0006755086,0.002131238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001621618,"about_ca_system_score_gemma":0.001382071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004894,"about_ca_topic_score_gemma":0.006326232,"domain_scores_codex":[0.995353,0.001294895,0.0008493377,0.0003611438,0.00195858,0.0001830933],"domain_scores_gemma":[0.988208,0.00663909,0.0006514842,0.0004739149,0.0036738,0.0003536909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001788692,0.0006289107,0.03636656,0.003462424,0.0009902864,0.0002870038,0.001655668,0.004832094,0.02602847,0.003535861,0.04448132,0.8759428],"study_design_scores_gemma":[0.001308075,0.002451283,0.2424374,0.001879541,0.003468357,0.001846021,0.009235322,0.5125539,0.06568526,0.01577494,0.1426434,0.0007165645],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.624468,0.009798467,0.2333002,0.001718922,0.001360824,0.004381546,0.02093773,0.0176977,0.08633658],"genre_scores_gemma":[0.7075821,0.004328355,0.2231202,0.0005764152,0.0002930911,0.002309177,0.05244909,0.001029868,0.008311694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009666724,"threshold_uncertainty_score":0.02815658,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963223838","doi":"","title":"WASSA-2017 shared task on emotion intensity","year":2019,"lang":"en","type":"article","venue":"Research Commons (University of Waikato)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":264,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sadness; Computer science; Task (project management); Anger; Emotion classification; Artificial intelligence; Natural language processing; Psychology; Social psychology","authors":[{"name":"Felipe Bravo-Márquez","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08052660557195573,"gpt":0.3063275320859715,"spread":0.2258009265140157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00806587,0.00444607,0.002859193,0.00351952,0.002894063,0.003927169,0.002971551,0.00321731,0.01523989],"category_scores_gemma":[0.02007667,0.000792961,0.002471271,0.002677865,0.00124316,0.005179639,0.008976122,0.004054253,0.02124421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002749275,"about_ca_system_score_gemma":0.003280031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009749731,"about_ca_topic_score_gemma":0.01392413,"domain_scores_codex":[0.989509,0.003093447,0.001201367,0.002280117,0.002710365,0.001205687],"domain_scores_gemma":[0.9838772,0.003893377,0.0007457546,0.004268094,0.004996216,0.002219355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002345748,0.001095751,0.007809568,0.001864765,0.0003626136,0.0004636546,0.001412308,0.00356844,0.02484287,0.002176755,0.8283376,0.1257199],"study_design_scores_gemma":[0.001441122,0.001959324,0.0475137,0.0006646079,0.0004486379,0.001200645,0.004381308,0.08970591,0.06503163,0.01690192,0.7701215,0.0006297081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.2226848,0.004293451,0.1085182,0.007406153,0.01103472,0.005498421,0.4861834,0.08375158,0.07062936],"genre_scores_gemma":[0.1788389,0.0004714559,0.08698969,0.001310112,0.0011077,0.004299963,0.6988781,0.004957399,0.02314668],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01523989,"threshold_uncertainty_score":0.05098253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982280746","doi":"10.2196/16023","title":"Sentiment Analysis in Health and Well-Being: Systematic Review","year":2019,"lang":"en","type":"review","venue":"JMIR Medical Informatics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":218,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Cardiff University","keywords":"Computer science; Data science","authors":[{"name":"Anastazia Žunić","is_ca":false},{"name":"Padraig Corcoran","is_ca":false},{"name":"‪Irena Spasić","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03407258699547368,"gpt":0.3668961208757042,"spread":0.3328235338802305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00927234,0.001472065,0.006034391,0.01052763,0.0007297547,0.00300656,0.001426794,0.001695421,0.005916917],"category_scores_gemma":[0.04723576,0.0006482071,0.006667694,0.008968943,0.001163105,0.002888686,0.001587892,0.001108091,0.0004751087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002752146,"about_ca_system_score_gemma":0.007869775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003900647,"about_ca_topic_score_gemma":0.01170626,"domain_scores_codex":[0.9925181,0.003038982,0.002400769,0.0005838925,0.001276512,0.0001817019],"domain_scores_gemma":[0.9485165,0.04086555,0.006682913,0.0004740832,0.003154814,0.000306143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001603416,0.00002080992,0.001077883,0.9185397,0.004120425,0.00007905327,0.000383323,0.00008216815,0.0001282586,0.0003215069,0.003278649,0.07180792],"study_design_scores_gemma":[0.0001379746,0.0001757613,0.006307575,0.9321696,0.02913004,0.0003195213,0.0007181702,0.0001506259,0.0001535351,0.0007105171,0.02997692,0.00004993761],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009937563,0.9971024,0.000199282,0.0004276841,0.0001634582,0.000299527,0.0004348873,0.000008904204,0.0003700214],"genre_scores_gemma":[0.01732807,0.9798068,0.000871949,0.0006583084,0.0001846175,0.0007247818,0.0002926105,0.000008517932,0.0001244395],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01052763,"threshold_uncertainty_score":0.0490374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001587475","doi":"10.1145/2009916.2010006","title":"ILDA","year":2011,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Interdependence; Probabilistic logic; Set (abstract data type); Product (mathematics); Task (project management); Topic model; Sentiment analysis; Component (thermodynamics); The Internet; Artificial intelligence; Data science; Interpretation (philosophy); Information retrieval; Natural language processing; Machine learning; World Wide Web; Mathematics; Engineering","authors":[{"name":"Samaneh Moghaddam","is_ca":true},{"name":"Martin Ester","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06601077421307201,"gpt":0.2262144582672276,"spread":0.1602036840541555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002650907,0.00164884,0.001017395,0.003465537,0.001762243,0.00609983,0.003007713,0.002428487,0.2459895],"category_scores_gemma":[0.01038254,0.0009152444,0.001874777,0.003359475,0.000632923,0.006360932,0.005635225,0.002292398,0.3152943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001396024,"about_ca_system_score_gemma":0.002178379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003621458,"about_ca_topic_score_gemma":0.005091664,"domain_scores_codex":[0.9964683,0.0006815991,0.0003418006,0.0009192733,0.001191378,0.0003977606],"domain_scores_gemma":[0.9955664,0.0007412248,0.0002170418,0.001774933,0.001335666,0.0003647188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000252983,0.0001202488,0.002073838,0.0006273858,0.00005975961,0.0002117705,0.0002204203,0.001261786,0.00237051,0.01820757,0.6651109,0.3094828],"study_design_scores_gemma":[0.00003087455,0.00003245264,0.0007762614,0.0001025761,0.0000198689,0.0002894095,0.0001055977,0.004109973,0.001341071,0.009239686,0.9839203,0.00003201756],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.006670188,0.004752877,0.2526715,0.005034859,0.003833041,0.001226866,0.09881213,0.1491715,0.477827],"genre_scores_gemma":[0.06375135,0.003963172,0.2091293,0.006384816,0.001389735,0.001881184,0.303612,0.02032731,0.3895612],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7540106,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2765183831","doi":"10.1177/0047287517729757","title":"Automated Sentiment Analysis in Tourism: Comparison of Approaches","year":2017,"lang":"en","type":"article","venue":"Journal of Travel Research","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mount Saint Vincent University","funders":"","keywords":"Sentiment analysis; Tourism; Computer science; Artificial intelligence; Machine learning; Hospitality; Data science; Selection (genetic algorithm); Natural language processing; Software; Data mining","authors":[{"name":"Andrei Kirilenko","is_ca":false},{"name":"Светлана Степченкова","is_ca":false},{"name":"Hany Kim","is_ca":true},{"name":"Xiang Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2825954453852928,"gpt":0.4573567636676105,"spread":0.1747613182823177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006491843,0.0008088463,0.0008357402,0.005484037,0.0007777702,0.002397097,0.0009777239,0.0008068783,0.001906176],"category_scores_gemma":[0.009626948,0.0003403737,0.001384556,0.002658494,0.0004796672,0.002148946,0.001375567,0.0007743071,0.001019389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00127617,"about_ca_system_score_gemma":0.001226246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00280704,"about_ca_topic_score_gemma":0.003886338,"domain_scores_codex":[0.9948298,0.00215472,0.0003942579,0.0004168163,0.001978867,0.0002255393],"domain_scores_gemma":[0.9933758,0.003270488,0.0004367871,0.0002941611,0.002385052,0.0002377205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001141385,0.0004170894,0.02689121,0.002291891,0.000768056,0.0001801603,0.002492904,0.007596267,0.007619666,0.005728784,0.01574096,0.9291317],"study_design_scores_gemma":[0.0005632327,0.002724502,0.2853138,0.002303003,0.001334019,0.001621855,0.01669559,0.4777155,0.02607214,0.03755054,0.1474731,0.0006326143],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5432182,0.02693555,0.2994159,0.00590961,0.002176847,0.002508223,0.002901418,0.0040996,0.1128346],"genre_scores_gemma":[0.7411186,0.01143773,0.2343694,0.000705339,0.0006850601,0.0007961158,0.00336995,0.0004197689,0.007098092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006491843,"threshold_uncertainty_score":0.03433251,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2274912527","doi":"10.1613/jair.4787","title":"How Translation Alters Sentiment","year":2016,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; National Research Council Canada","funders":"","keywords":"Sentiment analysis; Computer science; Focus (optics); Lexicon; Natural language processing; Annotation; Artificial intelligence; Arabic; Machine translation; Linguistics; Social media; Resource (disambiguation); World Wide Web","authors":[{"name":"Saif M. Mohammad","is_ca":true},{"name":"Mohammad Salameh","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2633291444881119,"gpt":0.4243514885302698,"spread":0.1610223440421579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002394137,0.0006790144,0.0003552284,0.0009247794,0.001173072,0.004771045,0.0004263674,0.00070978,0.01702052],"category_scores_gemma":[0.01474901,0.0004287495,0.0005320505,0.001254502,0.001463052,0.003518916,0.001529894,0.001296376,0.01270334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279678,"about_ca_system_score_gemma":0.00090314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002319514,"about_ca_topic_score_gemma":0.002002365,"domain_scores_codex":[0.9977748,0.00106805,0.0001317173,0.0003306279,0.0005039575,0.0001908782],"domain_scores_gemma":[0.9953225,0.001418985,0.0003359242,0.0007901826,0.001999461,0.0001328394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008309794,0.0002845692,0.02354581,0.001387391,0.0002117722,0.001993182,0.02977808,0.003664358,0.1133438,0.0991704,0.1018908,0.6238989],"study_design_scores_gemma":[0.0001987266,0.0004035354,0.05012467,0.0006311639,0.0003306621,0.002071302,0.02497181,0.03484488,0.08888031,0.1564288,0.6408977,0.0002164685],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4577627,0.002374702,0.1150093,0.02060382,0.005271306,0.0004782967,0.003121463,0.004523551,0.390855],"genre_scores_gemma":[0.9166805,0.00178429,0.03191848,0.003071344,0.0006489494,0.0002130937,0.002206742,0.002472757,0.0410038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01702052,"threshold_uncertainty_score":0.0569393,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047676437","doi":"10.1145/1871437.1871739","title":"Opinion digger","year":2010,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science","authors":[{"name":"Samaneh Moghaddam","is_ca":true},{"name":"Martin Ester","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01162528447042252,"gpt":0.261038368986786,"spread":0.2494130845163635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569349,0.0009348366,0.0007541674,0.004355069,0.0005055508,0.001280126,0.001283303,0.001093218,0.01104888],"category_scores_gemma":[0.007929564,0.0003774704,0.0007903444,0.002767131,0.0001906773,0.001822484,0.001054622,0.001078474,0.008130248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007229738,"about_ca_system_score_gemma":0.0007876269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002026476,"about_ca_topic_score_gemma":0.00750638,"domain_scores_codex":[0.9987889,0.0002116163,0.000132287,0.0003324901,0.0004398947,0.00009477857],"domain_scores_gemma":[0.9970385,0.001344355,0.0002861057,0.000367056,0.0008693665,0.00009472387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003784978,0.0002757382,0.007969287,0.0008789241,0.0001540398,0.0003210654,0.0002666273,0.002784213,0.009230797,0.005283509,0.2631738,0.7092834],"study_design_scores_gemma":[0.0003769234,0.0005694626,0.02222558,0.0002400377,0.0002894605,0.001219891,0.0005982482,0.4547552,0.06292029,0.03812168,0.4185121,0.0001712579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05958043,0.002209072,0.6511616,0.002843998,0.001267842,0.002454765,0.09775101,0.1339183,0.04881297],"genre_scores_gemma":[0.1910217,0.0009970017,0.6416436,0.001760492,0.0005356254,0.001803411,0.120799,0.00235083,0.03908831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01104888,"threshold_uncertainty_score":0.03696221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2760392765","doi":"10.18653/v1/d17-1056","title":"Refining Word Embeddings for Sentiment Analysis","year":2017,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Treebank; Word2vec; Sentiment analysis; Word (group theory); Natural language processing; Artificial intelligence; Context (archaeology); Parsing; Mathematics","authors":[{"name":"Liang-Chih Yu","is_ca":false},{"name":"Jin Wang","is_ca":false},{"name":"K. Robert Lai","is_ca":false},{"name":"Xuejie Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03981461137555894,"gpt":0.3329621635491202,"spread":0.2931475521735613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006764982,0.001336265,0.0005435007,0.001456536,0.0003098696,0.0007543931,0.0004688554,0.0005255713,0.003209107],"category_scores_gemma":[0.003893716,0.0002850178,0.0008051597,0.001250166,0.0003020208,0.003153665,0.0009376532,0.001163007,0.002731623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003805072,"about_ca_system_score_gemma":0.0004879596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001452195,"about_ca_topic_score_gemma":0.002550578,"domain_scores_codex":[0.9994978,0.000125572,0.00006272569,0.0001646564,0.0001030881,0.0000462782],"domain_scores_gemma":[0.9991187,0.000222709,0.0001092945,0.0001668444,0.0003477436,0.00003457105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000356187,0.0002495649,0.007443051,0.0002742022,0.0001271436,0.0001252885,0.0004268932,0.01582173,0.04616515,0.008738087,0.01952667,0.900746],"study_design_scores_gemma":[0.00006387237,0.0003163761,0.005715633,0.00008420065,0.0001346223,0.0002735127,0.0005649499,0.9067731,0.0287171,0.03460322,0.02268379,0.00006965417],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1383456,0.001106044,0.8474109,0.0005014366,0.0004548208,0.000297687,0.002016372,0.006087701,0.003779552],"genre_scores_gemma":[0.59065,0.0007706322,0.3934668,0.0002360325,0.0001706636,0.0003275265,0.008181259,0.000551394,0.005645738],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003209107,"threshold_uncertainty_score":0.01073557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2251902771","doi":"","title":"Cross-Linguistic Sentiment Analysis: From English to Spanish","year":2009,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":189,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Baseline (sea); Focus (optics); Sentiment analysis; Artificial intelligence; Adaptation (eye); English language; Support vector machine; Rule-based machine translation; Automation; Linguistics; Engineering; Psychology","authors":[{"name":"Julian Brooke","is_ca":true},{"name":"Milan Tofiloski","is_ca":true},{"name":"Maite Taboada","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01483167424319954,"gpt":0.2908510878003644,"spread":0.2760194135571649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001750719,0.0005768467,0.0003511551,0.001219148,0.000667679,0.001715471,0.0003427253,0.0003498786,0.006014281],"category_scores_gemma":[0.007182749,0.0001195833,0.0005170236,0.001588919,0.0003097077,0.00129664,0.001868399,0.0005296317,0.002657384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005445142,"about_ca_system_score_gemma":0.0003601731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008041213,"about_ca_topic_score_gemma":0.00710807,"domain_scores_codex":[0.9991565,0.0004411853,0.00006571677,0.0001197054,0.0001272064,0.00008972152],"domain_scores_gemma":[0.9969126,0.001249121,0.0001934903,0.000271191,0.001237508,0.0001360861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001628588,0.001287481,0.1416178,0.001096831,0.000420037,0.001610548,0.009789336,0.0050206,0.06752093,0.006213369,0.03702383,0.7267706],"study_design_scores_gemma":[0.0003735669,0.001120245,0.5206388,0.0007115144,0.0008919072,0.002296366,0.03345831,0.1026011,0.0854373,0.0212519,0.2309247,0.0002942949],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8956769,0.002442936,0.04276853,0.001706816,0.0005341497,0.0002480325,0.003702928,0.001000852,0.05191879],"genre_scores_gemma":[0.9547448,0.001338282,0.0279352,0.0004992895,0.0002036474,0.0002303829,0.00658309,0.0003988873,0.008066479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008041213,"threshold_uncertainty_score":0.02011979,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W187058510","doi":"","title":"Analyzing Appraisal Automatically","year":2004,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":180,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Natural language processing; Orientation (vector space); Product (mathematics); Information retrieval; Artificial intelligence; Content (measure theory); Mathematics","authors":[{"name":"Maite Taboada","is_ca":true},{"name":"Jack Grieve","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01577781097010012,"gpt":0.28993734860876,"spread":0.2741595376386599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002360338,0.0009984395,0.0005950057,0.005615801,0.000777479,0.002128077,0.0007113757,0.0005762022,0.009327335],"category_scores_gemma":[0.02676453,0.000366267,0.0005111753,0.003538693,0.0004160358,0.00315708,0.0009893841,0.00112834,0.006671231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009018277,"about_ca_system_score_gemma":0.0009610888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001594686,"about_ca_topic_score_gemma":0.002096141,"domain_scores_codex":[0.9958099,0.0008985005,0.0003221221,0.0008478885,0.001942056,0.0001793951],"domain_scores_gemma":[0.9819636,0.006520789,0.001601065,0.001151242,0.008528258,0.0002351177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003332723,0.0001429658,0.01601842,0.001134373,0.00006428034,0.0005130822,0.003335426,0.002553381,0.0317332,0.02241462,0.05612251,0.8656344],"study_design_scores_gemma":[0.0001352596,0.0004541419,0.08241735,0.0008181544,0.0002420675,0.001378767,0.004024413,0.2932485,0.0623213,0.105458,0.4491798,0.0003223664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1100959,0.001167464,0.7860301,0.001450971,0.0009792919,0.001329161,0.0110112,0.008490715,0.0794452],"genre_scores_gemma":[0.3595964,0.0007992422,0.5938525,0.0003129599,0.0008957515,0.001666566,0.01673181,0.001437491,0.02470729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009327335,"threshold_uncertainty_score":0.03120297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1808640434","doi":"10.1007/978-3-540-68825-9_3","title":"A Comparison of Sentiment Analysis Techniques: Polarizing Movie Blogs","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Popularity; Sentiment analysis; Polarity (international relations); Social media; Set (abstract data type); Support vector machine; Visualization; Task (project management); The Internet; Information retrieval; World Wide Web; Data science; Service (business); Artificial intelligence; Machine learning","authors":[{"name":"Michelle Annett","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03004770387279265,"gpt":0.3035841228788185,"spread":0.2735364190060259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003548695,0.000999455,0.00105649,0.006950273,0.0006797587,0.002601187,0.000597952,0.0007616802,0.002508867],"category_scores_gemma":[0.01056956,0.0003143139,0.001008128,0.005880913,0.0003068954,0.002988907,0.001049752,0.0007176234,0.001918787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003121003,"about_ca_system_score_gemma":0.0004872202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00127955,"about_ca_topic_score_gemma":0.003607293,"domain_scores_codex":[0.9975917,0.0009884769,0.0001637101,0.0002352171,0.0008848355,0.0001361201],"domain_scores_gemma":[0.988485,0.007671511,0.0004096671,0.0003988739,0.00274063,0.0002942297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002650351,0.00039084,0.01939701,0.001695438,0.0007068453,0.00009598213,0.001261598,0.001607856,0.02541288,0.001595802,0.01213833,0.9330471],"study_design_scores_gemma":[0.001178017,0.005866482,0.3744168,0.00135474,0.00391878,0.002158866,0.0177266,0.4109911,0.07717949,0.01986685,0.08463454,0.0007078307],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.646394,0.02341715,0.258808,0.002017992,0.001819802,0.001112335,0.00777291,0.0040115,0.05464631],"genre_scores_gemma":[0.6676213,0.01238764,0.2998609,0.0003245595,0.00109126,0.0004657963,0.00924283,0.0006547198,0.00835093],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006950273,"threshold_uncertainty_score":0.01876754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161926933","doi":"","title":"When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging","year":2008,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Software portability; Computer science; Lexicon; WordNet; Classifier (UML); Artificial intelligence; Annotation; Natural language processing; Domain (mathematical analysis); Weighting; Sentiment analysis; Precision and recall; Training set; Information retrieval; Machine learning","authors":[{"name":"Alina Andreevskaia","is_ca":true},{"name":"Sabine Bergler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02636169918772258,"gpt":0.2488749297044931,"spread":0.2225132305167705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02769392,0.001072511,0.001452278,0.002653231,0.003135177,0.003791571,0.001828966,0.00226803,0.001544212],"category_scores_gemma":[0.06544276,0.00134934,0.000558907,0.002377756,0.001936355,0.01160647,0.005958196,0.002943568,0.001579573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001379257,"about_ca_system_score_gemma":0.001770449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004898302,"about_ca_topic_score_gemma":0.008711512,"domain_scores_codex":[0.9816595,0.009872016,0.0009905916,0.004459599,0.00218264,0.0008356997],"domain_scores_gemma":[0.938006,0.04112229,0.004731069,0.007109711,0.007329383,0.001701615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002550084,0.0004662247,0.1921034,0.0006986744,0.0003789397,0.00180399,0.03173734,0.005962857,0.05361289,0.005449903,0.01673001,0.6885058],"study_design_scores_gemma":[0.0004517911,0.001507519,0.2427695,0.0006436647,0.001206253,0.005366868,0.0443457,0.4564839,0.07398529,0.09377737,0.07884892,0.0006130913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6405157,0.001013668,0.3263978,0.004118028,0.0005961139,0.0006499055,0.000556861,0.002284439,0.02386751],"genre_scores_gemma":[0.9310318,0.0002158095,0.0626994,0.0014106,0.0002909647,0.0001936798,0.0007507794,0.0004464383,0.002960481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02769392,"threshold_uncertainty_score":0.1464611,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166048187","doi":"10.1016/j.dss.2012.05.030","title":"From once upon a time to happily ever after: Tracking emotions in mail and books","year":2012,"lang":"en","type":"article","venue":"Decision Support Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sentiment analysis; Affect (linguistics); Tracking (education); Computer science; Psychology; Negative emotion; Natural language processing; Social psychology; Communication","authors":[{"name":"Saif M. Mohammad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02628875647228958,"gpt":0.277846949778926,"spread":0.2515581933066364,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007783289,0.0002992409,0.0002471308,0.001515512,0.0005544046,0.002197048,0.00033068,0.0006303618,0.00224702],"category_scores_gemma":[0.007360221,0.0001456516,0.0001730593,0.001432769,0.0002013481,0.001669452,0.0004930144,0.0006005175,0.002131954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006095358,"about_ca_system_score_gemma":0.0002238872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00518448,"about_ca_topic_score_gemma":0.0124155,"domain_scores_codex":[0.9994794,0.0001556619,0.00004462693,0.00009645616,0.0001662051,0.00005772247],"domain_scores_gemma":[0.9952768,0.002906902,0.0005454948,0.0001335136,0.0008845495,0.0002527453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001938925,0.0007272452,0.5579321,0.0004869227,0.0002401133,0.0008567465,0.008416316,0.002285021,0.01372105,0.00090075,0.06029886,0.3521958],"study_design_scores_gemma":[0.00003966342,0.0003339972,0.8920228,0.0001235841,0.000232183,0.0004383092,0.01608089,0.05621628,0.01010015,0.001625522,0.02269335,0.00009320046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890698,0.000535119,0.00275532,0.0005065714,0.0001089991,0.00005436768,0.00270959,0.0004461895,0.003814152],"genre_scores_gemma":[0.9843386,0.0002611885,0.006337681,0.0001479046,0.0001447431,0.00005588787,0.00336481,0.00006777245,0.005281466],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00518448,"threshold_uncertainty_score":0.01030856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W45569842","doi":"10.1111/j.1467-8640.2012.00417.x","title":"MULTI‐DOCUMENT SUMMARIZATION OF EVALUATIVE TEXT","year":2012,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":161,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Multi-document summarization; Information retrieval; Natural language processing","authors":[{"name":"Giuseppe Carenini","is_ca":true},{"name":"Adam Pauls","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06534615047374848,"gpt":0.3594688220181262,"spread":0.2941226715443778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003716193,0.001004386,0.0008305039,0.003064961,0.0006395458,0.001882617,0.0007136964,0.0004940515,0.002051737],"category_scores_gemma":[0.01248914,0.0002154585,0.000514236,0.001776002,0.0003116023,0.002010418,0.0008648583,0.0007171534,0.0008171114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004651042,"about_ca_system_score_gemma":0.0006926849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008543456,"about_ca_topic_score_gemma":0.002092478,"domain_scores_codex":[0.997834,0.0009254996,0.0002050697,0.0003335257,0.0006304194,0.00007140281],"domain_scores_gemma":[0.9893249,0.006204506,0.001132569,0.0008959732,0.00226507,0.0001769866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007010719,0.0002697457,0.003193327,0.002494202,0.0002552228,0.0004657605,0.003862092,0.02059484,0.05382628,0.00736103,0.01266152,0.8943149],"study_design_scores_gemma":[0.0003343265,0.002972913,0.02531066,0.001148338,0.001300725,0.001134247,0.007524317,0.4869731,0.2127789,0.0627846,0.1973114,0.000426467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1800574,0.006438655,0.7936422,0.001246708,0.0003972281,0.00109889,0.003322202,0.005309477,0.008487305],"genre_scores_gemma":[0.3974231,0.001878847,0.5881038,0.0002195079,0.0003876661,0.0005769414,0.005441586,0.0003755236,0.005593092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003716193,"threshold_uncertainty_score":0.01965332,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1930223417","doi":"10.1109/tmm.2015.2482228","title":"Deep Multimodal Learning for Affective Analysis and Retrieval","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Modalities; Social media; Upload; Representation (politics); Multimodal learning; Artificial intelligence; Emotion classification; Feature learning; Multimodality; Information retrieval; Automatic summarization; Natural language processing; Machine learning; World Wide Web","authors":[{"name":"Lei Pang","is_ca":false},{"name":"Shiai Zhu","is_ca":true},{"name":"Chong‐Wah Ngo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02515312700733929,"gpt":0.2826347932597046,"spread":0.2574816662523653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006730882,0.0009776065,0.0007968089,0.0007319768,0.0003032569,0.0008682192,0.001115021,0.001109663,0.006524211],"category_scores_gemma":[0.002177099,0.0003747465,0.0009621768,0.0006816185,0.0004170392,0.001338329,0.001138432,0.001645646,0.002333327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001067686,"about_ca_system_score_gemma":0.0005326145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004763507,"about_ca_topic_score_gemma":0.005869602,"domain_scores_codex":[0.9996704,0.00009546856,0.00001541377,0.00009182242,0.00005746215,0.00006952172],"domain_scores_gemma":[0.9997131,0.0001231762,0.00002856685,0.00004309198,0.00007104952,0.00002093159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004714043,0.000294555,0.001199952,0.000344168,0.0002410723,0.0001864293,0.0001884819,0.1833394,0.02487327,0.01463244,0.02354128,0.7506876],"study_design_scores_gemma":[0.000009355235,0.00003439012,0.0003706567,0.00001862357,0.00002527723,0.0000295514,0.00002899943,0.9843126,0.002672591,0.01064494,0.001842621,0.0000104911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03024559,0.005126139,0.9527043,0.001085291,0.0001908643,0.00008879975,0.0006512976,0.004039088,0.005868631],"genre_scores_gemma":[0.7954228,0.002934275,0.1764014,0.001204501,0.0003592447,0.0003198353,0.002580319,0.0004072527,0.02037026],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006524211,"threshold_uncertainty_score":0.02182561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2913898221","doi":"10.1109/access.2019.2892852","title":"A Hybrid Framework for Sentiment Analysis Using Genetic Algorithm Based Feature Reduction","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University; McGill University","funders":"Zayed University","keywords":"Computer science; Sentiment analysis; Lexicon; Artificial intelligence; Scalability; Machine learning; Feature (linguistics); Rough set; Data mining; Algorithm","authors":[{"name":"Farkhund Iqbal","is_ca":false},{"name":"Jahanzeb Maqbool Hashmi","is_ca":false},{"name":"Benjamin C. M. Fung","is_ca":true},{"name":"Rabia Batool","is_ca":false},{"name":"Asad Masood Khattak","is_ca":false},{"name":"Saiqa Aleem","is_ca":false},{"name":"Patrick C. K. Hung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03052181447566905,"gpt":0.3267984758927722,"spread":0.2962766614171032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005773483,0.0008726926,0.0008119042,0.00121867,0.000357355,0.0008380525,0.000903492,0.0006140551,0.001201697],"category_scores_gemma":[0.001110225,0.0003110547,0.001130187,0.001020093,0.000359774,0.0006226309,0.0004890879,0.0006627095,0.000497257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006029514,"about_ca_system_score_gemma":0.0006559654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005153752,"about_ca_topic_score_gemma":0.003461852,"domain_scores_codex":[0.9996252,0.00008503536,0.00002046762,0.00007459192,0.0001572256,0.00003747043],"domain_scores_gemma":[0.9997395,0.00008742321,0.00002780166,0.00002217298,0.0001142807,0.000008922661],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001373942,0.0002045626,0.001783382,0.0001596498,0.0001964593,0.0002303548,0.0002115363,0.4399354,0.04378464,0.01731115,0.003588408,0.492457],"study_design_scores_gemma":[0.00001154652,0.00004090873,0.0002573468,0.000005279772,0.00001717584,0.00003302042,0.00001581003,0.9924896,0.002492406,0.003191518,0.00143453,0.00001088812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006685457,0.00008664388,0.9913935,0.00006258019,0.00002861002,0.00005715931,0.00004254148,0.0008014082,0.0008420834],"genre_scores_gemma":[0.1564299,0.0001653568,0.8406226,0.0001133001,0.00004311788,0.0003206054,0.0003093417,0.0001418492,0.001853897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005153752,"threshold_uncertainty_score":0.01024747,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313294355","doi":"10.1080/0144929x.2022.2156387","title":"Machine learning techniques for emotion detection and sentiment analysis: current state, challenges, and future directions","year":2022,"lang":"en","type":"article","venue":"Behaviour and Information Technology","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"California State Council on Developmental Disabilities; Directorate for Engineering","keywords":"Current (fluid); Sentiment analysis; Emotion detection; State (computer science); Computer science; Cognitive psychology; Psychology; Data science; Artificial intelligence; Cognitive science; Emotion recognition; Engineering; Electrical engineering","authors":[{"name":"Alaa Alslaity","is_ca":true},{"name":"Rita Orji","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0116577232750635,"gpt":0.2512381424678022,"spread":0.2395804191927387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02024981,0.001231334,0.002360219,0.005403507,0.0005869125,0.004004875,0.002331871,0.002357528,0.003070383],"category_scores_gemma":[0.02599262,0.0007718796,0.002167399,0.005169496,0.001679981,0.008666362,0.00136012,0.003261753,0.001690757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001958688,"about_ca_system_score_gemma":0.003388125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002645769,"about_ca_topic_score_gemma":0.00271294,"domain_scores_codex":[0.9937687,0.003043421,0.0006921738,0.0006598876,0.001611476,0.0002243382],"domain_scores_gemma":[0.9441785,0.04453698,0.002339909,0.0007831318,0.007775649,0.0003858146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007611937,0.0001213336,0.002022338,0.01414747,0.0001833661,0.00003963384,0.0002978881,0.0007706708,0.0005947558,0.006587046,0.009939548,0.9652199],"study_design_scores_gemma":[0.0002077291,0.001033304,0.02178517,0.09755198,0.001715584,0.001007818,0.004866148,0.04117461,0.005584563,0.1167295,0.7079034,0.0004400997],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001306357,0.9739428,0.0128825,0.009258359,0.0005417295,0.00008656264,0.00008266752,0.00010485,0.001794153],"genre_scores_gemma":[0.01842598,0.9405724,0.03529859,0.00266378,0.001631028,0.0003257794,0.0002145543,0.00004637947,0.0008213806],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.02024981,"threshold_uncertainty_score":0.1070926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W135937222","doi":"10.1007/978-3-642-21043-3_8","title":"Using a Heterogeneous Dataset for Emotion Analysis in Text","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Disgust; Sadness; Surprise; Computer science; Support vector machine; Anger; Happiness; Emotion classification; Artificial intelligence; Sentiment analysis; Classifier (UML); Emotion detection; Machine learning; Natural language processing; Emotion recognition; Psychology; Social psychology","authors":[{"name":"Soumaya Chaffar","is_ca":true},{"name":"Diana Inkpen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0635249034249282,"gpt":0.3016810333679441,"spread":0.2381561299430159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001523992,0.001134299,0.0007991258,0.004089664,0.0009870097,0.001784952,0.0008664803,0.001249349,0.002906675],"category_scores_gemma":[0.004934798,0.0002384819,0.0009642733,0.003302747,0.0002418622,0.002104942,0.001633393,0.001101209,0.002453136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006104454,"about_ca_system_score_gemma":0.0004463383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002012625,"about_ca_topic_score_gemma":0.004369305,"domain_scores_codex":[0.998161,0.0004162164,0.0002255684,0.0005186172,0.0005492226,0.0001292579],"domain_scores_gemma":[0.9969421,0.001109685,0.0002291892,0.0005428114,0.0009382329,0.0002379772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002585177,0.002973346,0.05167202,0.001754773,0.0009924815,0.001794997,0.001040274,0.009658718,0.1372679,0.003111938,0.2117633,0.5753849],"study_design_scores_gemma":[0.0007415943,0.001703582,0.2288023,0.0004753677,0.001429496,0.002835927,0.004411711,0.4266075,0.09704387,0.0146861,0.2208027,0.0004598546],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5666075,0.002815135,0.1675795,0.002300418,0.002745432,0.0019858,0.2321585,0.008845051,0.0149627],"genre_scores_gemma":[0.4487499,0.0007335874,0.1611267,0.000579681,0.0009026116,0.001729562,0.380226,0.0004674965,0.005484497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004089664,"threshold_uncertainty_score":0.009723842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036568251","doi":"10.1016/j.inffus.2020.06.002","title":"Deep learning based emotion analysis of microblog texts","year":2020,"lang":"en","type":"article","venue":"Information Fusion","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"National Key Research and Development Program of China; Natural Science Foundation of Shandong Province; Key Technology Research and Development Program of Shandong; National Natural Science Foundation of China","keywords":"Word2vec; Computer science; Microblogging; Artificial intelligence; Sentiment analysis; Convolutional neural network; Natural language processing; Support vector machine; Word (group theory); Feature (linguistics); Social media; Convolution (computer science); Feature vector; Artificial neural network; Pattern recognition (psychology); World Wide Web; Mathematics","authors":[{"name":"Dongliang Xu","is_ca":false},{"name":"Zhihong Tian","is_ca":false},{"name":"Rufeng Lai","is_ca":false},{"name":"Xiangtao Kong","is_ca":false},{"name":"Zhiyuan Tan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01235506478018438,"gpt":0.2257955153964658,"spread":0.2134404506162814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005396774,0.0005539678,0.0003652349,0.001208941,0.00025497,0.000740794,0.0002749376,0.0004125402,0.001587084],"category_scores_gemma":[0.001439012,0.0001034279,0.0004345694,0.0008328187,0.0001467329,0.0009703184,0.0004501797,0.0007604485,0.0009891688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003935795,"about_ca_system_score_gemma":0.0002586068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00194756,"about_ca_topic_score_gemma":0.002986867,"domain_scores_codex":[0.9996722,0.00006881891,0.00002412327,0.0000586576,0.0001001189,0.00007621214],"domain_scores_gemma":[0.9994162,0.0002041729,0.00006928036,0.00002696284,0.0002516141,0.00003165132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008694697,0.0007825097,0.01353961,0.0003411061,0.0002454438,0.0003274859,0.0005880944,0.02630393,0.1422445,0.003330962,0.01813273,0.7932942],"study_design_scores_gemma":[0.00001373055,0.0001612289,0.01467587,0.00003029193,0.00009205576,0.00008866494,0.0002927307,0.9537624,0.02359917,0.00330156,0.003958308,0.00002405663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6013192,0.002459528,0.3806805,0.00138985,0.0006284368,0.0001530331,0.002376401,0.001876062,0.009116975],"genre_scores_gemma":[0.9537739,0.0005621277,0.03793789,0.0001086599,0.0002300004,0.00005444191,0.001815211,0.00005981201,0.005458019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00194756,"threshold_uncertainty_score":0.005309343,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295710275","doi":"10.3115/v1/n15-1078","title":"Sentiment after Translation: A Case-Study on Arabic Social Media Posts","year":2015,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Alberta","funders":"","keywords":"Arabic; Computer science; Social media; Natural language processing; Computational linguistics; Linguistics; Artificial intelligence; Machine translation; World Wide Web; Philosophy","authors":[{"name":"Mohammad Salameh","is_ca":true},{"name":"Saif M. Mohammad","is_ca":true},{"name":"Svetlana Kiritchenko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09888186726437186,"gpt":0.3132161652834242,"spread":0.2143342980190523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238211,0.0004597628,0.0002333996,0.001077308,0.002418195,0.001870229,0.000467127,0.001119661,0.004328924],"category_scores_gemma":[0.01287425,0.0001504767,0.0002644967,0.001795875,0.0007587933,0.001909073,0.0009972545,0.0007015126,0.002177968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006590896,"about_ca_system_score_gemma":0.0007241453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003014258,"about_ca_topic_score_gemma":0.004713076,"domain_scores_codex":[0.9983254,0.0009416612,0.00009558145,0.000124462,0.0003598349,0.0001530708],"domain_scores_gemma":[0.991056,0.004869569,0.0008726121,0.0004866531,0.002427135,0.0002880488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001726057,0.002203948,0.1285299,0.001945094,0.0001208304,0.04803025,0.2769109,0.00158031,0.03886756,0.00798359,0.03701724,0.4550844],"study_design_scores_gemma":[0.0001599263,0.001709428,0.1916805,0.0009425195,0.0003775081,0.0263052,0.4321808,0.03005649,0.05616575,0.008549333,0.2516165,0.0002560942],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97409,0.0003540294,0.004866779,0.002028874,0.0002189966,0.0002240756,0.0005311588,0.0001265995,0.01755938],"genre_scores_gemma":[0.9826177,0.0005229294,0.007066461,0.0005620825,0.000143165,0.00009349236,0.0008017088,0.0001580274,0.008034458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004328924,"threshold_uncertainty_score":0.01448172,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045584434","doi":"10.1016/j.eswa.2012.12.084","title":"Sentiment polarity detection in Spanish reviews combining supervised and unsupervised approaches","year":2012,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Artificial intelligence; Machine learning; Classifier (UML); Sentiment analysis; Unsupervised learning; Polarity (international relations); Supervised learning; Natural language processing; Pattern recognition (psychology); Artificial neural network","authors":[{"name":"María Teresa Martín Valdivia","is_ca":false},{"name":"Eugenio Martínez‐Cámara","is_ca":false},{"name":"José M. Perea‐Ortega","is_ca":false},{"name":"Luís Alfonso Ureña López","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05847855461083074,"gpt":0.2670254764919242,"spread":0.2085469218810935,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001811107,0.0006298225,0.0005755359,0.002768425,0.0004204319,0.001167509,0.0002539972,0.0003616233,0.001068198],"category_scores_gemma":[0.007331188,0.0001353897,0.0004824927,0.001305315,0.0001503846,0.0005745712,0.0003831922,0.0003083528,0.001010616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000394324,"about_ca_system_score_gemma":0.0007422221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003000031,"about_ca_topic_score_gemma":0.005756351,"domain_scores_codex":[0.9984249,0.0006694747,0.0001390908,0.0002203556,0.0004250614,0.0001211804],"domain_scores_gemma":[0.9927845,0.001646283,0.0007368058,0.0002236124,0.004409327,0.0001994706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001513151,0.0004519216,0.2620333,0.001771367,0.0004855914,0.0008073703,0.002143784,0.002018102,0.09973361,0.001176103,0.03087968,0.596986],"study_design_scores_gemma":[0.0001699293,0.0008119774,0.7358437,0.0005028333,0.0009602722,0.001252651,0.004763535,0.1265225,0.06186768,0.002541757,0.0646139,0.0001493068],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9135394,0.003505404,0.0557332,0.0006591586,0.0005058728,0.0004385067,0.004541989,0.001027404,0.02004913],"genre_scores_gemma":[0.95399,0.001091492,0.03293512,0.0001151353,0.0004501842,0.0002359234,0.004945677,0.0001231028,0.006113214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003000031,"threshold_uncertainty_score":0.009578109,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385570923","doi":"10.18653/v1/2023.acl-long.421","title":"ConFEDE: Contrastive Feature Decomposition for Multimodal Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Modalities; Sentiment analysis; Modality (human–computer interaction); Feature (linguistics); Representation (politics); Natural language processing; Feature learning; Decomposition; Pattern recognition (psychology); Linguistics","authors":[{"name":"Jiuding Yang","is_ca":true},{"name":"Yakun Yu","is_ca":true},{"name":"Di Niu","is_ca":true},{"name":"Weidong Guo","is_ca":false},{"name":"Yu Xu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0179968430349941,"gpt":0.3187499885937276,"spread":0.3007531455587335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001490445,0.001430287,0.0008676924,0.001889352,0.0003438962,0.0008461733,0.0008107681,0.0007420222,0.003686826],"category_scores_gemma":[0.004221481,0.0002174179,0.001161993,0.001236029,0.0003558974,0.001492091,0.001207243,0.001577663,0.001419938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006333913,"about_ca_system_score_gemma":0.0005003838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001746078,"about_ca_topic_score_gemma":0.003036061,"domain_scores_codex":[0.9994749,0.0001387535,0.00003246095,0.0001287016,0.000164072,0.00006118133],"domain_scores_gemma":[0.9992487,0.0002810647,0.00007913501,0.0001016533,0.0002480652,0.00004144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005322889,0.0003609077,0.003505704,0.0003007412,0.0002619312,0.0001680364,0.0001964846,0.02621596,0.05778601,0.006943455,0.02738216,0.8763462],"study_design_scores_gemma":[0.00007171022,0.0002734512,0.005129165,0.00004221223,0.00008865949,0.0001608007,0.0001532948,0.9475959,0.01896977,0.01472447,0.01274022,0.00005029985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0523793,0.001251183,0.9339295,0.0004282486,0.0002212546,0.0003492424,0.002125915,0.004718387,0.004596992],"genre_scores_gemma":[0.4804743,0.0008018628,0.5024387,0.0004276565,0.0002986368,0.0007209649,0.008563341,0.0004245182,0.005850014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003686826,"threshold_uncertainty_score":0.01233363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}