{"id":"W4285100697","doi":"10.2196/preprints.40403","title":"Development of a COVID-19–Related Anti-Asian Tweet Data Set: Quantitative Study (Preprint)","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Institute for Christian Studies; University of Toronto","funders":"","keywords":"Computer science; Social media; Set (abstract data type); Data set; Coronavirus disease 2019 (COVID-19); Stigma (botany); Preprint; Information retrieval; Artificial intelligence; World Wide Web; Psychology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007858763,0.0003322136,0.0003773141,0.003046847,0.001376181,0.001234431,0.001057129,0.0009305891,0.006803999],"category_scores_gemma":[0.0279672,0.0002675175,0.0003939049,0.003102414,0.0009536752,0.001750247,0.001718162,0.001578474,0.004919519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001231651,"about_ca_system_score_gemma":0.001576233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007629224,"about_ca_topic_score_gemma":0.01028553,"domain_scores_codex":[0.9946689,0.002605035,0.0005203913,0.0006587994,0.001349692,0.0001971229],"domain_scores_gemma":[0.9626275,0.02197535,0.001787172,0.003051414,0.009151481,0.001406997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001176194,0.005936964,0.3037187,0.00478213,0.0001984027,0.001422646,0.02713693,0.008536285,0.02078759,0.01222226,0.3152502,0.2988316],"study_design_scores_gemma":[0.0004229182,0.001953498,0.5919692,0.0009571488,0.000115334,0.0007668291,0.04105888,0.05260351,0.02412056,0.005622306,0.2799736,0.0004362441],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7049779,0.0002196851,0.04016849,0.002733153,0.0004264308,0.00955372,0.2311771,0.002077802,0.008665687],"genre_scores_gemma":[0.4942389,0.000251395,0.1329053,0.0009285862,0.0002429546,0.02807567,0.3359947,0.0006683401,0.006694035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007858763,"threshold_uncertainty_score":0.04156166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1049700189319252,"score_gpt":0.3591974746514637,"score_spread":0.2542274557195385,"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."}}