{"id":"W4401115349","doi":"10.1371/journal.pdig.0000545","title":"Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022","year":2024,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada); Regional Municipality of Niagara; Brock University; Response Biomedical (Canada); University of Toronto; York University","funders":"International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Lexicon; Annotation; Computer science; Artificial intelligence; Natural language processing; Labeled data; Transformer; Social media; Machine learning; Engineering","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":[0.000386112,0.0001020437,0.0002508214,0.0002075291,0.00006384005,0.0001511355,0.0002028869,0.0000267624,0.000006238191],"category_scores_gemma":[0.00006539249,0.00009968287,0.00009691613,0.0005539207,0.00001281049,0.0006522819,0.00003973666,0.00004934623,0.000006387455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040404,"about_ca_system_score_gemma":0.0002819811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004519225,"about_ca_topic_score_gemma":0.00001810344,"domain_scores_codex":[0.9984595,0.00004456977,0.0005261032,0.0003363916,0.0004461359,0.0001872687],"domain_scores_gemma":[0.999011,0.0003062927,0.0002203621,0.0002465453,0.0001366408,0.00007913482],"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":[0.0000431283,0.0002827447,0.0004772243,0.001466667,0.0001742524,9.394619e-7,0.004477404,0.05372769,0.01100428,0.004205602,0.0001487881,0.9239913],"study_design_scores_gemma":[0.0001884311,0.0003792553,0.0002806077,0.0004401466,0.00001269088,1.345285e-7,0.00007786648,0.9849067,0.009471294,0.004144251,0.00001365943,0.00008497245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3762087,0.000362554,0.622404,0.0003648839,0.000149184,0.0003037224,0.00007432931,0.00007588244,0.00005675349],"genre_scores_gemma":[0.9730868,0.000002687546,0.02666038,0.0001023216,0.00003644991,0.0000333061,0.00003942769,0.00001105314,0.00002753635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.931179,"threshold_uncertainty_score":0.4064949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1097679616781885,"score_gpt":0.38802400234012,"score_spread":0.2782560406619314,"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."}}