{"id":"W4388527109","doi":"10.36948/ijfmr.2023.v05i05.8248","title":"Improvement of Accuracy for Hate Speech Detection Using Modified Feature Extraction","year":2023,"lang":"en","type":"article","venue":"International Journal For Multidisciplinary Research","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"tf–idf; Offensive; Computer science; Gradient boosting; Boosting (machine learning); Logistic regression; Artificial intelligence; Feature extraction; Identification (biology); Classifier (UML); The Internet; Natural language processing; Machine learning; Speech recognition; Term (time); Random forest; World Wide Web; 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":[0.003404003,0.001462219,0.001639029,0.00207623,0.0005865677,0.001302986,0.001170005,0.001441666,0.00255165],"category_scores_gemma":[0.01047298,0.0002603646,0.001073217,0.001021855,0.0003034139,0.001973504,0.001139694,0.001091843,0.005927772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004303462,"about_ca_system_score_gemma":0.0007228171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006206093,"about_ca_topic_score_gemma":0.005249762,"domain_scores_codex":[0.9973637,0.000654174,0.0001683598,0.0006921752,0.0007286969,0.0003928304],"domain_scores_gemma":[0.9947748,0.002224495,0.0002891407,0.0009161484,0.001651442,0.0001439534],"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":[0.001253538,0.0007221707,0.03975072,0.0003179367,0.0002179443,0.0003435574,0.0001926174,0.01653253,0.04470273,0.0005686036,0.01505481,0.8803428],"study_design_scores_gemma":[0.00006005042,0.0006929063,0.04464323,0.00008980091,0.0001942287,0.000984362,0.0003901933,0.8748993,0.06875751,0.001130062,0.008055453,0.0001029281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6434302,0.004216419,0.3117384,0.001123041,0.001060898,0.0003858556,0.003176249,0.02297328,0.01189558],"genre_scores_gemma":[0.8936372,0.0006069712,0.09561634,0.0001804811,0.000136639,0.00007339131,0.003644351,0.0002266866,0.005877905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006206093,"threshold_uncertainty_score":0.01800233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1410024468009056,"score_gpt":0.4661950302775791,"score_spread":0.3251925834766735,"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."}}