{"id":"W4401043462","doi":"10.18653/v1/2024.naacl-long.236","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Speech recognition","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001673933,0.0001219969,0.0001581072,0.0004665842,0.00009874532,0.001597043,0.0003463853,0.00003732813,0.0000856192],"category_scores_gemma":[0.00008338707,0.0001010779,0.00006058264,0.002386519,0.00003532553,0.002692514,0.000113339,0.0001328302,0.0001458888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005549029,"about_ca_system_score_gemma":0.00002098104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00173102,"about_ca_topic_score_gemma":0.0008546649,"domain_scores_codex":[0.998748,0.00004413233,0.000246608,0.0005216053,0.0002297591,0.000209893],"domain_scores_gemma":[0.9993921,0.00008465116,0.00002417439,0.000320687,0.00009233581,0.00008603704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004508842,0.0001239827,0.07778046,0.00005493495,0.0009733457,0.0003327542,0.02273121,0.003509491,0.006285602,0.02320555,0.003850828,0.8611068],"study_design_scores_gemma":[0.001068188,0.0003258908,0.4578477,0.0003503884,0.0003117233,0.00004215966,0.007787636,0.383547,0.0953993,0.00966138,0.04139267,0.002265937],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9138832,0.00004739723,0.08365103,0.000215889,0.00118184,0.00009505945,0.0001795759,0.0003879742,0.0003580073],"genre_scores_gemma":[0.9669228,0.0000394439,0.03238703,0.00006897993,0.0001454079,0.00004303001,0.0002894421,0.000004267615,0.00009964768],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8588408,"threshold_uncertainty_score":0.9994394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06829547400335344,"score_gpt":0.3002132387230232,"score_spread":0.2319177647196698,"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."}}