{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000252251,0.0005117501,0.0008836322,0.0007098504,0.000132266,0.0001677887,0.001063434,0.0003775494,0.00001938563],"category_scores_gemma":[0.00004779482,0.0005649081,0.0002867907,0.000442051,0.0001147477,0.0001987684,0.002480842,0.001413003,0.000001359459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003139829,"about_ca_system_score_gemma":0.0004666369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001952796,"about_ca_topic_score_gemma":0.0001876969,"domain_scores_codex":[0.9965659,0.000148793,0.001328527,0.001016543,0.0004997208,0.0004405396],"domain_scores_gemma":[0.996982,0.00007864702,0.001213401,0.001325304,0.000269685,0.000130961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008150309,0.003813453,0.08535963,0.003378422,0.0005687721,0.01791461,0.01994642,0.02109658,0.01601068,0.0009823455,0.007801825,0.8230458],"study_design_scores_gemma":[0.0168912,0.005727679,0.3371372,0.0305276,0.002085452,0.007205496,0.004283724,0.1923371,0.1630448,0.006458052,0.2126695,0.02163229],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9181371,0.0008298152,0.07533912,0.00005061268,0.00252116,0.001719623,0.00006954068,0.0004364165,0.0008966514],"genre_scores_gemma":[0.923255,0.0000900314,0.07417121,0.0001474663,0.000116224,0.0003984488,0.00108587,0.00003704272,0.0006987443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8014135,"threshold_uncertainty_score":0.9996802,"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."}}