{"id":"W4411120416","doi":"10.18653/v1/2025.naacl-long.92","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","year":2025,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Commission; DeepMind; Universität Hamburg; International Development Research Centre; Rockefeller Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Speech recognition","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001691899,0.001492983,0.0009463495,0.006152905,0.001872829,0.001462448,0.001624996,0.001901699,0.008381484],"category_scores_gemma":[0.005858236,0.0004885275,0.0009202048,0.003432394,0.0005769177,0.00266783,0.004128759,0.001370163,0.009879515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007285713,"about_ca_system_score_gemma":0.001552888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01854517,"about_ca_topic_score_gemma":0.03694308,"domain_scores_codex":[0.9985619,0.0004193506,0.0002042415,0.0002683424,0.0003083093,0.0002378487],"domain_scores_gemma":[0.9972595,0.0007221299,0.0003460039,0.000640346,0.0006514891,0.0003806232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001037323,0.0005948276,0.05605039,0.002461778,0.0003301964,0.001214258,0.002765246,0.0009641456,0.006648444,0.00206359,0.8053827,0.1204871],"study_design_scores_gemma":[0.0003179717,0.0002261379,0.2664214,0.0008830106,0.0002450601,0.001909154,0.008234546,0.005418384,0.006231284,0.00176123,0.7080877,0.0002640763],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.08523067,0.003550237,0.005331473,0.001595804,0.0008779582,0.0005456727,0.8862935,0.005035871,0.01153881],"genre_scores_gemma":[0.04703039,0.0005791189,0.006682759,0.0001856527,0.0001439767,0.000875325,0.93989,0.0002886172,0.004324139],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01854517,"threshold_uncertainty_score":0.03687447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00752431814208908,"score_gpt":0.2785270477125188,"score_spread":0.2710027295704297,"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."}}