{"id":"W4389518407","doi":"10.18653/v1/2023.banglalp-1.9","title":"Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation","year":2023,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Bengali; Computer science; Artificial intelligence","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":[0.0006880665,0.001125025,0.0005973775,0.004683823,0.000966043,0.001027944,0.0008880418,0.001558727,0.003574951],"category_scores_gemma":[0.003299103,0.0002205292,0.0006356522,0.002543688,0.0003572476,0.001280854,0.001992109,0.0007180688,0.005117887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006297574,"about_ca_system_score_gemma":0.0007943878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0119841,"about_ca_topic_score_gemma":0.04166434,"domain_scores_codex":[0.9989574,0.000260538,0.0001176103,0.0002779243,0.0002641603,0.0001223665],"domain_scores_gemma":[0.9981178,0.0005456787,0.0002204261,0.0003580111,0.0004079019,0.000350176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002716762,0.001507874,0.1763227,0.006211822,0.0008425079,0.004008705,0.00420745,0.003872194,0.03189107,0.003044856,0.5159119,0.2494622],"study_design_scores_gemma":[0.0002751022,0.0009551222,0.4871609,0.0007712887,0.0003439329,0.004216882,0.008897766,0.02700276,0.01123908,0.002987266,0.4558449,0.0003049346],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2714337,0.00351333,0.008426273,0.001110544,0.001033917,0.001130209,0.6913664,0.004339688,0.01764601],"genre_scores_gemma":[0.164403,0.001081719,0.01688443,0.0003651867,0.0003440007,0.001162032,0.8068038,0.0002705864,0.008685247],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0119841,"threshold_uncertainty_score":0.02382869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04972597408164969,"score_gpt":0.30801025010299,"score_spread":0.2582842760213404,"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."}}