{"id":"W4362575702","doi":"10.22215/etd/2023-15400","title":"Empirical Study on Improving Hate Speech Detection: Novel BERT based One-Versus-All Classification Approach (BOVAC) with a Novel Performance Metric: Global Performance (GP)","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Voice activity detection; Metric (unit); Task (project management); Artificial intelligence; Natural language processing; Process (computing); Speech recognition; Performance metric; Speech processing; Empirical research; Machine learning; Engineering; Mathematics","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":[0.01285026,0.001939695,0.001657435,0.002044102,0.001323587,0.001890109,0.001929041,0.002175017,0.001894698],"category_scores_gemma":[0.03538707,0.0002997666,0.0008079166,0.00169116,0.001148007,0.003953638,0.00181661,0.003356323,0.00208314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001529093,"about_ca_system_score_gemma":0.0009699501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004421001,"about_ca_topic_score_gemma":0.004992726,"domain_scores_codex":[0.9895993,0.005470267,0.0005405481,0.001610807,0.002283335,0.0004957277],"domain_scores_gemma":[0.9626235,0.02420372,0.001897404,0.004610633,0.005586714,0.001078095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002973103,0.002097405,0.04928093,0.001151207,0.0005655083,0.0001853989,0.001039238,0.05587417,0.02376892,0.003757701,0.02795306,0.8313534],"study_design_scores_gemma":[0.0001890511,0.00548035,0.05451942,0.0001409559,0.0003544942,0.0006384161,0.001281409,0.8804391,0.04088215,0.005785704,0.01011254,0.0001764742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8254141,0.007946669,0.1445817,0.00211321,0.0008355464,0.0006307618,0.00201941,0.003799956,0.0126586],"genre_scores_gemma":[0.9164055,0.0004974027,0.07577172,0.0003672392,0.0002362628,0.0001273665,0.002842691,0.0002437128,0.003508031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01285026,"threshold_uncertainty_score":0.06795955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1107862799980144,"score_gpt":0.331530699441937,"score_spread":0.2207444194439226,"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."}}