{"id":"W4406450848","doi":"10.48550/arxiv.2501.08284","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Commission; DeepMind; Universität Hamburg; International Development Research Centre; Rockefeller Foundation","keywords":"Computer science; Linguistics; Natural language processing; Political science","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":[0.00155879,0.001722841,0.0007493261,0.00564975,0.002376072,0.001416812,0.001657828,0.002038785,0.007502389],"category_scores_gemma":[0.005865566,0.0003991649,0.0008623333,0.004184292,0.0009631907,0.002084628,0.003909381,0.00156257,0.01162732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101796,"about_ca_system_score_gemma":0.001513535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02066809,"about_ca_topic_score_gemma":0.04848089,"domain_scores_codex":[0.998298,0.0004348886,0.0002054227,0.0003939615,0.0003652684,0.0003025857],"domain_scores_gemma":[0.9964722,0.000863538,0.0004563685,0.0008876903,0.0008856989,0.0004345],"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":[0.0007988732,0.0006208564,0.04953947,0.002592156,0.0001691672,0.001522447,0.005967696,0.001318292,0.01220188,0.002983955,0.8183404,0.1039448],"study_design_scores_gemma":[0.0001450891,0.0001746834,0.1806868,0.0006921992,0.00008650422,0.00156969,0.007374882,0.003862239,0.007660832,0.002118045,0.7954065,0.0002225104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.09605881,0.001596052,0.005791463,0.001226258,0.0005413846,0.0006556957,0.8715202,0.006070979,0.01653921],"genre_scores_gemma":[0.03939362,0.0003169331,0.009532542,0.0002167655,0.0001004047,0.000807216,0.9450274,0.0003598563,0.004245349],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02066809,"threshold_uncertainty_score":0.04109555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02078586480009493,"score_gpt":0.2966906162401926,"score_spread":0.2759047514400976,"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."}}