{"id":"W2955549617","doi":"10.18653/v1/w18-5103","title":"A Review of Standard Text Classification Practices for Multi-label Toxicity Identification of Online Content","year":2018,"lang":"en","type":"review","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"International Medias Data Services (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Support vector machine; Inference; Natural language processing; Social media; Machine learning; Language identification; Speech recognition; Natural language; World Wide Web","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":[0.006697922,0.001603857,0.002273719,0.01011475,0.0007025838,0.002439263,0.002801835,0.001648776,0.003187402],"category_scores_gemma":[0.01793052,0.0006270135,0.001597134,0.005589276,0.0009499079,0.003467321,0.0008973278,0.001720789,0.004573927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167925,"about_ca_system_score_gemma":0.001873243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002617102,"about_ca_topic_score_gemma":0.00314056,"domain_scores_codex":[0.9962872,0.0008708208,0.0004973363,0.0008415553,0.001396558,0.0001064614],"domain_scores_gemma":[0.9825577,0.01088974,0.001321735,0.0007749743,0.004232336,0.0002234927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004381203,0.00007802553,0.001494037,0.00844301,0.0001343205,0.00004470146,0.000135533,0.000538645,0.001591378,0.001637468,0.01630913,0.96955],"study_design_scores_gemma":[0.0000713058,0.0007408667,0.02624965,0.02906479,0.001522127,0.002859737,0.001058165,0.02200794,0.02368027,0.01788154,0.8744731,0.0003904946],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00630236,0.8805261,0.09080192,0.003411789,0.00199997,0.000732278,0.002187121,0.001632381,0.01240616],"genre_scores_gemma":[0.05713284,0.8006042,0.1188471,0.002834372,0.002851485,0.001249293,0.005983702,0.0004336424,0.01006333],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01011475,"threshold_uncertainty_score":0.03542244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3275048838604004,"score_gpt":0.4401816853434807,"score_spread":0.1126768014830802,"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."}}