{"id":"W3162322285","doi":"10.32473/flairs.v34i1.128427","title":"Ensemble-based Semi-Supervised Learning for Hate Speech Detection","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Leverage (statistics); Computer science; Ensemble learning; Artificial intelligence; Labeled data; Voice activity detection; Machine learning; Supervised learning; Natural language processing; Speech recognition; Speech processing; Artificial neural network","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":[0.005103146,0.001126832,0.001581562,0.001845325,0.001022001,0.000974222,0.001562021,0.001110582,0.0009493916],"category_scores_gemma":[0.009548173,0.0003779428,0.0008465806,0.001125069,0.0005979693,0.002088226,0.001471798,0.002173918,0.001273582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005224153,"about_ca_system_score_gemma":0.0009507631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001947384,"about_ca_topic_score_gemma":0.004772728,"domain_scores_codex":[0.9969516,0.001472572,0.0001881873,0.0006118056,0.0005909257,0.0001850221],"domain_scores_gemma":[0.9885105,0.005722246,0.0007110747,0.001970976,0.00279549,0.0002897355],"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":[0.0004373593,0.0008244459,0.01798414,0.0001794381,0.0004450811,0.0001508141,0.0004169355,0.1499227,0.01178408,0.002814559,0.009624645,0.8054157],"study_design_scores_gemma":[0.00000825084,0.00007761239,0.001400719,0.00001348296,0.00002806001,0.00005152336,0.00006405133,0.9891426,0.004939832,0.00319556,0.001060429,0.00001779822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09105749,0.0007111533,0.9020253,0.0002642722,0.0001265957,0.000169305,0.0004734782,0.003007617,0.002164801],"genre_scores_gemma":[0.6770008,0.0003019876,0.3164909,0.0002274905,0.0002093175,0.0003077808,0.002947837,0.0001773787,0.002336488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005103146,"threshold_uncertainty_score":0.02698833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1015021418685871,"score_gpt":0.3376627144692195,"score_spread":0.2361605726006324,"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."}}