{"meta":{"query_hash":"e0f3ea994abf","filters":{"venue":"Online Social Networks and Media"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e0f3ea994abf","api":"https://metacan.xera.ac/api/v1/cohort?venue=Online+Social+Networks+and+Media"},"results":[{"id":"W2981441564","doi":"10.1016/j.osnem.2019.100054","title":"From associations to sarcasm: Mining the shift of opinions regarding the Supreme Court on twitter","year":2019,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Law in Society and Culture","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Furman University","keywords":"Sarcasm; Supreme court; Social media; Political science; Law; Psychology; Irony; Art; Literature","score_opus":0.030648720970468897,"score_gpt":0.31110552009970494,"score_spread":0.28045679912923605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981441564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98110116,0.0007516729,0.0006732942,0.0012403639,0.00015983434,0.000041522148,0.0074439757,0.000054172346,0.008533932],"genre_scores_gemma":[0.98685396,0.00041579054,0.0009494042,0.0002759503,0.00030501542,0.00008805346,0.008393971,0.000033814507,0.002684054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989343,0.00032421848,0.000115619194,0.00020291124,0.0002738428,0.0001490507],"domain_scores_gemma":[0.9920067,0.0045360103,0.0018486828,0.0003398729,0.0007931244,0.0004755972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007486473,0.00032079426,0.00027511697,0.0033757412,0.0008949818,0.0017632943,0.00048594168,0.0010768432,0.0030603048],"category_scores_gemma":[0.010726734,0.00015022281,0.00033983772,0.0044322163,0.00049251673,0.0023217062,0.0013787224,0.0009787071,0.002289589],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071243674,0.00026311062,0.8392865,0.0005293946,0.00031654615,0.0010500704,0.01565384,0.00075958576,0.00539663,0.0021777812,0.034905646,0.09894843],"study_design_scores_gemma":[0.000021840782,0.00018347803,0.8903069,0.00026122638,0.00018728676,0.0010112573,0.043732215,0.009560309,0.0020152975,0.004064637,0.048586357,0.000069135036],"about_ca_topic_score_codex":0.003877221,"about_ca_topic_score_gemma":0.010990892,"teacher_disagreement_score":0.003877221,"about_ca_system_score_codex":0.00039397425,"about_ca_system_score_gemma":0.00041998428,"threshold_uncertainty_score":0.010237753},"labels":[],"label_agreement":null},{"id":"W3037316620","doi":"10.1016/j.osnem.2020.100079","title":"A deep learning model for Twitter spam detection","year":2020,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Commission; Concordia University of Edmonton","keywords":"Popularity; Computer science; Spambot; Social media; Spamming; World Wide Web; Machine learning; The Internet; Artificial intelligence; Data science","score_opus":0.032567200454107645,"score_gpt":0.25293061868753103,"score_spread":0.22036341823342337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037316620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.097077146,0.0020055517,0.8880258,0.0025784355,0.0004205413,0.00010985949,0.0013918402,0.0035821034,0.004808612],"genre_scores_gemma":[0.83116955,0.00093788054,0.14175725,0.0010145846,0.00042529881,0.00021188855,0.0024279284,0.00017259142,0.02188299],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997285,0.000055307257,0.000015282762,0.00007318598,0.00006196015,0.000065818254],"domain_scores_gemma":[0.99919826,0.00031882408,0.00006194655,0.00006962474,0.00029570158,0.00005557483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086443685,0.00079556234,0.0008288496,0.00085494615,0.0005006789,0.000772518,0.0014074375,0.0016036716,0.0024622655],"category_scores_gemma":[0.0024114512,0.0005087323,0.0006134342,0.0007723126,0.00040715875,0.0013871818,0.0011394204,0.0018377596,0.0013614473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041195934,0.00052954163,0.005613038,0.00014382447,0.00018348615,0.00013237329,0.000082116836,0.4080052,0.0071509844,0.008949465,0.025271628,0.5435264],"study_design_scores_gemma":[0.0000038290605,0.0000140253815,0.00014171767,0.0000045857932,0.000008881182,0.0000071114055,0.0000029854386,0.99710864,0.0005675304,0.0017741551,0.00036335434,0.0000030917256],"about_ca_topic_score_codex":0.012753626,"about_ca_topic_score_gemma":0.016007494,"teacher_disagreement_score":0.012753626,"about_ca_system_score_codex":0.0010266545,"about_ca_system_score_gemma":0.0013063947,"threshold_uncertainty_score":0.025358796},"labels":[],"label_agreement":null},{"id":"W3087096149","doi":"10.1016/j.osnem.2020.100096","title":"Hate and offensive speech detection on Arabic social media","year":2020,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Offensive; Computer science; Annotation; Natural language processing; Artificial intelligence; Social media; Class (philosophy); Crawling; Variety (cybernetics); Arabic; Speech recognition; Machine learning; Linguistics; World Wide Web","score_opus":0.02048245754773978,"score_gpt":0.22785761133351823,"score_spread":0.20737515378577845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087096149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9821951,0.00048339585,0.008226806,0.000146626,0.000109824294,0.00006560924,0.0011509866,0.00042634952,0.007195321],"genre_scores_gemma":[0.9909689,0.00018291916,0.0047966363,0.00004049492,0.00007326419,0.00003300683,0.0006524227,0.000015009064,0.0032373406],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999556,0.000101227226,0.000024611076,0.00006776038,0.00017048774,0.000079773505],"domain_scores_gemma":[0.9985997,0.0005248755,0.00021848726,0.00010892108,0.00039531384,0.00015267772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039705524,0.00049636065,0.00022909482,0.0025400913,0.0005356616,0.0005763628,0.0001735347,0.00053870113,0.0023614562],"category_scores_gemma":[0.0019534049,0.000086769134,0.0001998598,0.0006872559,0.00024726233,0.00043286209,0.0005815726,0.0003568512,0.0015699601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023046604,0.0006949639,0.2899293,0.00059223414,0.00019442728,0.0032463565,0.0025622556,0.0033674098,0.1992951,0.0014623866,0.010786305,0.48556465],"study_design_scores_gemma":[0.00003150744,0.0008434921,0.6693813,0.00011193659,0.00020648124,0.0050402754,0.0055344426,0.19280906,0.10959678,0.0010416001,0.015264525,0.00013858781],"about_ca_topic_score_codex":0.0021242353,"about_ca_topic_score_gemma":0.0033217536,"teacher_disagreement_score":0.0025400913,"about_ca_system_score_codex":0.00021536462,"about_ca_system_score_gemma":0.00020829559,"threshold_uncertainty_score":0.007899821},"labels":[],"label_agreement":null},{"id":"W3159506318","doi":"10.1016/j.osnem.2022.100203","title":"Community detection for access-control decisions: Analysing the role of homophily and information diffusion in Online Social Networks","year":2022,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme","keywords":"Homophily; Diffusion; Social network (sociolinguistics); Control (management); Internet privacy; Social media; Computer science; Online community; Access control; Business; Data science; World Wide Web; Sociology; Computer security; Social science; Artificial intelligence","score_opus":0.01258324695676144,"score_gpt":0.2822564075746142,"score_spread":0.26967316061785274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159506318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6724721,0.0012153292,0.32136896,0.001162133,0.00006121304,0.00023096811,0.00023600247,0.0003271972,0.0029261094],"genre_scores_gemma":[0.9804198,0.00016135925,0.018710379,0.000037421898,0.000024552295,0.000044327986,0.00009134681,0.000019649013,0.00049127144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975151,0.001335998,0.00008849789,0.00044814343,0.00038782417,0.00022454833],"domain_scores_gemma":[0.9554283,0.036262676,0.0036286016,0.0017352247,0.0016895949,0.0012554849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063126264,0.0006270709,0.0010548458,0.0028141378,0.001086602,0.0022821506,0.0015986048,0.0017485522,0.0013898542],"category_scores_gemma":[0.03443989,0.00046595666,0.0010483159,0.0012846623,0.0013899091,0.0036893215,0.001793849,0.0016344656,0.00020210055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050872256,0.000624495,0.06258599,0.00039402823,0.00037703323,0.0006471255,0.0017876312,0.76992756,0.005152241,0.07900408,0.0022161668,0.07677498],"study_design_scores_gemma":[0.00000837385,0.000032437685,0.00205608,0.0000137582365,0.000015629752,0.000054571305,0.000107462445,0.9873789,0.00032742377,0.009763632,0.000229126,0.000012752545],"about_ca_topic_score_codex":0.0073089297,"about_ca_topic_score_gemma":0.0042787613,"teacher_disagreement_score":0.0073089297,"about_ca_system_score_codex":0.0015666321,"about_ca_system_score_gemma":0.0010396092,"threshold_uncertainty_score":0.03338474},"labels":[],"label_agreement":null},{"id":"W4210798472","doi":"10.1016/j.osnem.2021.100194","title":"Selecting and combining complementary feature representations and classifiers for hate speech detection","year":2022,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Heuristics; Sarcasm; Artificial intelligence; Feature selection; Machine learning; Feature extraction; Task (project management); Selection (genetic algorithm); Speech recognition; Natural language processing","score_opus":0.0194614751732331,"score_gpt":0.2694540405599481,"score_spread":0.249992565386715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210798472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27046463,0.0024992712,0.71557033,0.0006948172,0.0005951515,0.0004167679,0.0009771311,0.0033650782,0.0054168133],"genre_scores_gemma":[0.7983771,0.00074882363,0.19385178,0.00028848628,0.00033820546,0.0002514768,0.0017887572,0.00013322172,0.004222097],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99829835,0.00030380665,0.000094077215,0.0004563473,0.00044425903,0.0004031084],"domain_scores_gemma":[0.9976271,0.0009842872,0.00012990627,0.0002097476,0.0009039066,0.00014510445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025120906,0.0018043298,0.0021969373,0.0040526073,0.0007458005,0.0019189479,0.0010746876,0.0018167581,0.0018114141],"category_scores_gemma":[0.00516578,0.00044055207,0.0016593459,0.0023332126,0.0004588403,0.0020716055,0.0016247767,0.0013674124,0.0016494358],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076530053,0.0010384955,0.014872788,0.00016752254,0.00035708735,0.00022326337,0.00011294202,0.010455566,0.061022386,0.0009553825,0.005757495,0.90427166],"study_design_scores_gemma":[0.00008191239,0.0007598845,0.028583188,0.00007637579,0.00087368797,0.0004856442,0.00049516134,0.8985497,0.06075902,0.005040651,0.0041690324,0.0001257093],"about_ca_topic_score_codex":0.00339231,"about_ca_topic_score_gemma":0.004617471,"teacher_disagreement_score":0.0040526073,"about_ca_system_score_codex":0.0004878076,"about_ca_system_score_gemma":0.0010979851,"threshold_uncertainty_score":0.0132853985},"labels":[],"label_agreement":null},{"id":"W4221124614","doi":"10.1016/j.osnem.2022.100204","title":"Comparing global tourism flows measured by official census and social sensing","year":2022,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Census; Tourism; Geography; Social media; Data science; Regional science; Cartography; Computer science; World Wide Web; Sociology; Demography","score_opus":0.029262620880836837,"score_gpt":0.288108298189393,"score_spread":0.2588456773085561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221124614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599873,0.00034185566,0.0024523214,0.00014001926,0.00004841752,0.00004184616,0.024630843,0.000117226125,0.012240215],"genre_scores_gemma":[0.9711609,0.0003247279,0.0021047767,0.000020226475,0.000022434686,0.000039866234,0.025140205,0.000022627448,0.0011642998],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996101,0.00011191556,0.000038722603,0.00008171855,0.000092453476,0.00006505175],"domain_scores_gemma":[0.9986808,0.00030254823,0.00041090127,0.0001647595,0.0003610215,0.0000800821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056088826,0.00033462167,0.00015041775,0.0042674784,0.00018571595,0.0006457782,0.00018274538,0.00016879321,0.001706667],"category_scores_gemma":[0.0024797288,0.00007357871,0.00032650548,0.005474005,0.00024991448,0.00091110286,0.0007152253,0.00022318728,0.00040959264],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024291204,0.00008207587,0.9392644,0.00034315238,0.00033806305,0.0001222901,0.00094530487,0.0071719326,0.00094199984,0.0030836891,0.0067675933,0.04069646],"study_design_scores_gemma":[0.0000057091506,0.000057618385,0.9804866,0.00005373913,0.0000578268,0.00011091712,0.0025669078,0.006383394,0.0005404025,0.00046191324,0.009253417,0.000021591508],"about_ca_topic_score_codex":0.034259323,"about_ca_topic_score_gemma":0.04771956,"teacher_disagreement_score":0.034259323,"about_ca_system_score_codex":0.0004621723,"about_ca_system_score_gemma":0.00045290045,"threshold_uncertainty_score":0.068119824},"labels":[],"label_agreement":null},{"id":"W4408249562","doi":"10.1016/j.osnem.2025.100307","title":"An explainable ensemble model for revealing the level of depression in social media by considering personality traits and sentiment polarity pattern","year":2025,"lang":"en","type":"article","venue":"Online Social Networks and Media","topic":"Mental Health via Writing","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi; Lembaga Pengelola Dana Pendidikan; Kementerian Pendidikan dan Kebudayaan","keywords":"Social media; Polarity (international relations); Big Five personality traits; Sentiment analysis; Depression (economics); Personality; Psychology; Computer science; Data science; Artificial intelligence; Cognitive psychology; Social psychology; World Wide Web; Biology; Economics","score_opus":0.10656637902635882,"score_gpt":0.3939350347637808,"score_spread":0.287368655737422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408249562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8257041,0.0005525302,0.16345128,0.0013389223,0.0002698918,0.000102211234,0.0036674722,0.0006277825,0.0042858166],"genre_scores_gemma":[0.98484486,0.00012794767,0.009483989,0.0000755835,0.00008409928,0.000081849816,0.0016656042,0.000026762722,0.0036093309],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99977547,0.000054111264,0.000010969576,0.00009407115,0.000022557577,0.000042883985],"domain_scores_gemma":[0.99930394,0.0003579257,0.00008452808,0.00005982123,0.00014603011,0.00004769419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070388155,0.000815781,0.0006065397,0.00075816887,0.00040295246,0.0008256182,0.00082269084,0.00072735036,0.0027702474],"category_scores_gemma":[0.002070285,0.00027971424,0.0008587734,0.0006015644,0.00020762993,0.0008624064,0.00056190277,0.00096204435,0.00073556864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007855582,0.00087866077,0.30474183,0.00013441457,0.0014167211,0.00081884686,0.0006383782,0.48679003,0.008624901,0.011112698,0.011382672,0.17267525],"study_design_scores_gemma":[0.00000815127,0.000047016918,0.020852756,0.0000094640645,0.00008087302,0.0000528757,0.0000365044,0.97478026,0.00019691304,0.0035360975,0.00038308985,0.00001598046],"about_ca_topic_score_codex":0.0108445855,"about_ca_topic_score_gemma":0.010865449,"teacher_disagreement_score":0.0108445855,"about_ca_system_score_codex":0.0003484735,"about_ca_system_score_gemma":0.00041937458,"threshold_uncertainty_score":0.021562934},"labels":[],"label_agreement":null}]}