{"id":"W4312084660","doi":"10.1016/j.dib.2022.108832","title":"A curated dataset for hate speech detection on social media text","year":2022,"lang":"en","type":"article","venue":"Data in Brief","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Lakehead University","keywords":"Computer science; Slang; Social media; Natural language processing; Preprocessor; Vocabulary; Classifier (UML); Sentence; Artificial intelligence; Perplexity; Speech recognition; Information retrieval; World Wide Web; Linguistics; Language model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007214791,0.0001072843,0.0001214575,0.0001543125,0.0003976175,0.0001341596,0.001367908,0.00004190115,0.00005318414],"category_scores_gemma":[0.000227791,0.0001191121,0.00002164348,0.0006148518,0.00002152733,0.0005413142,0.0007825621,0.000247264,0.00004973794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009263329,"about_ca_system_score_gemma":0.00004601761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002352748,"about_ca_topic_score_gemma":0.0004613131,"domain_scores_codex":[0.9985429,0.0001124057,0.0001966623,0.0005587823,0.0003172065,0.0002720643],"domain_scores_gemma":[0.9988058,0.0001351261,0.0001060026,0.0008875612,0.00002159483,0.00004393683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001333237,0.0001563404,0.00001124698,0.00001265355,0.00001343734,0.00005163569,0.0003404596,0.00006075093,0.002417317,0.001024321,0.117354,0.8784245],"study_design_scores_gemma":[0.001270683,0.0002160884,0.001091522,0.000007618934,0.0000088644,0.00005626676,0.0001031728,0.05077063,0.009800116,0.001296441,0.9350541,0.0003245291],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2508531,0.0001833423,0.575952,0.008258015,0.0132337,0.003968962,0.1450443,0.001428965,0.001077615],"genre_scores_gemma":[0.9459094,0.00001558983,0.007183395,0.001479747,0.0005359508,0.0002703869,0.04447765,0.00003636794,0.00009156096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8781,"threshold_uncertainty_score":0.485725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05926111213507972,"score_gpt":0.2942761866840025,"score_spread":0.2350150745489228,"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."}}