{"id":"W1961993270","doi":"10.1002/asi.23533","title":"A machine‐learning approach to negation and speculation detection for sentiment analysis","year":2015,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Negation; Speculation; Scope (computer science); Computer science; Artificial intelligence; Baseline (sea); Task (project management); Sentiment analysis; Natural language processing; Machine learning; Identification (biology); Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003080512,0.00005057388,0.0001254426,0.001223375,0.0003081689,0.0002937888,0.0002580601,0.00005171451,1.198988e-7],"category_scores_gemma":[0.001397447,0.00003671635,0.00005724986,0.002819963,0.00002629082,0.001811818,0.00009141624,0.00006647278,4.798092e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002132474,"about_ca_system_score_gemma":0.00006868684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002838386,"about_ca_topic_score_gemma":0.000001888052,"domain_scores_codex":[0.9989781,0.00001832862,0.0003327912,0.00008650539,0.0004719089,0.0001123637],"domain_scores_gemma":[0.9975469,0.00005045868,0.000796679,0.0000911542,0.001463457,0.00005137774],"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":[0.0001224894,0.0001548376,0.2605748,0.00004864926,0.001138266,8.7867e-8,0.01789184,0.07659107,0.006773692,0.2659928,0.001351702,0.3693598],"study_design_scores_gemma":[0.0007165504,0.0001632413,0.007706382,0.000005416608,0.0001478987,0.000006802471,0.0007763416,0.9678242,0.004529313,0.00355578,0.01448065,0.00008740751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08386243,0.00002660501,0.9119681,0.003341786,0.0002239499,0.0002713554,0.000001370472,0.00002097342,0.00028341],"genre_scores_gemma":[0.9803642,0.000005026137,0.01944056,0.0001024571,0.00002038866,0.000008974192,0.000001511387,0.000001091859,0.00005578111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8965018,"threshold_uncertainty_score":0.2833012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581222229712936,"score_gpt":0.2586530080846184,"score_spread":0.242840785787489,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}