{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002774516,0.0001307643,0.0001501384,0.00097451,0.0007207588,0.0003429128,0.0009324347,0.0001219637,0.000005535173],"category_scores_gemma":[0.0005641097,0.0001199214,0.0002217623,0.0006170969,0.0000486301,0.0009636668,0.0003320551,0.0004482097,0.00001115356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002952655,"about_ca_system_score_gemma":0.0001624528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005252308,"about_ca_topic_score_gemma":0.00002448338,"domain_scores_codex":[0.9976319,0.00007895647,0.0003940657,0.0003515489,0.001080526,0.0004629776],"domain_scores_gemma":[0.9967384,0.0006143872,0.0002571298,0.0002371402,0.002031324,0.0001216685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005496702,0.0001069342,0.00003003662,0.00003975814,0.0001017441,0.00003155558,0.0003987501,0.004051925,0.7403057,0.0004751347,0.0005667062,0.253342],"study_design_scores_gemma":[0.001235368,0.0006446637,0.0005939975,0.00008292361,0.00000752139,0.0002243205,0.0004191711,0.6146561,0.3661122,0.01412667,0.001759529,0.0001375208],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5480481,0.00002721988,0.4458814,0.001831431,0.003338816,0.0007163198,0.0000290267,0.0000733565,0.00005433121],"genre_scores_gemma":[0.9730381,0.00009233654,0.02444687,0.000009722986,0.0008697258,0.000109942,0.00002134304,0.00002484581,0.001387146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6106042,"threshold_uncertainty_score":0.5543567,"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."}}