{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002227236,0.0001973452,0.0002142535,0.0001322447,0.0007053282,0.0008230943,0.001946072,0.0001622678,0.00005546758],"category_scores_gemma":[0.001869183,0.0001760554,0.000389223,0.001210534,0.0002356389,0.0006266777,0.0005757969,0.0007671627,0.00003178647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002551182,"about_ca_system_score_gemma":0.0004476213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000852781,"about_ca_topic_score_gemma":0.00004035001,"domain_scores_codex":[0.9967236,0.00005457744,0.0005132316,0.000681288,0.001457823,0.0005695153],"domain_scores_gemma":[0.9931443,0.0004502333,0.0002049895,0.0002563128,0.005820449,0.0001237485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007353141,0.00009520501,0.000139367,0.00009288476,0.00006677448,0.000001382427,0.0009067326,0.0006212663,0.7946385,0.06590591,0.0003404059,0.137118],"study_design_scores_gemma":[0.00005462334,0.00008437897,0.00002432478,0.00008992251,0.000005227126,0.0000076928,0.001051961,0.3283182,0.6384166,0.03037995,0.001448454,0.0001186241],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2261693,0.00004960882,0.7598013,0.007484033,0.001790504,0.0007203536,0.000007419265,0.0001819721,0.003795493],"genre_scores_gemma":[0.9817951,0.00008121198,0.01641374,0.000112642,0.0003562587,0.0001262974,0.000004369744,0.00001858727,0.001091782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7556258,"threshold_uncertainty_score":0.7937117,"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."}}