{"id":"W4410298309","doi":"10.1016/j.chbr.2026.101154","title":"Towards a Comprehensive Taxonomy of Online Abusive Language Informed by Machine Learning","year":2025,"lang":"en","type":"preprint","venue":"Computers in Human Behavior Reports","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Taxonomy (biology); Computer science; Natural language processing; Artificial intelligence; Psychology; Ecology; Biology","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":[0.009633811,0.001465855,0.001475189,0.01791233,0.003256839,0.007928262,0.00245768,0.002148482,0.001483391],"category_scores_gemma":[0.03230101,0.0007835791,0.001794842,0.01240388,0.003256918,0.01174348,0.005479594,0.003644498,0.001219934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002873584,"about_ca_system_score_gemma":0.007628253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01016721,"about_ca_topic_score_gemma":0.01304755,"domain_scores_codex":[0.988632,0.004097871,0.002105214,0.00168067,0.002878812,0.000605386],"domain_scores_gemma":[0.9637852,0.01655092,0.005329673,0.004041191,0.009218788,0.001074275],"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":[0.0001919852,0.0009243104,0.3054774,0.002570744,0.0002956757,0.0006963427,0.02256784,0.01552508,0.007491714,0.09523021,0.0172064,0.5318223],"study_design_scores_gemma":[0.0000654699,0.000463057,0.1403948,0.003014395,0.0002704341,0.001703649,0.02767006,0.3336534,0.007064782,0.405443,0.07984197,0.0004150504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1414995,0.003339902,0.8265554,0.005526615,0.0001729464,0.002601922,0.006371811,0.001475735,0.01245614],"genre_scores_gemma":[0.2945795,0.001804594,0.6898395,0.0007202469,0.00007840773,0.00243152,0.008876232,0.0001327663,0.001537223],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01791233,"threshold_uncertainty_score":0.05094904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02788481802931132,"score_gpt":0.299750038058015,"score_spread":0.2718652200287037,"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."}}