{"id":"W4407874572","doi":"10.1177/0261927x251318887","title":"Automating the Detection of Linguistic Intergroup Bias Through Computerized Language Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Language and Social Psychology","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Lexical analysis; Abstraction; Ingroups and outgroups; Coding (social sciences); Computer science; Outgroup; Natural language processing; Linguistics; Sentence; Psychology; Sentiment analysis; Linguistic analysis; Artificial intelligence; Cognitive psychology; Social psychology; Statistics; Mathematics; Epistemology","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":[0.0005303836,0.00007565255,0.0002733385,0.00021029,0.0001297225,0.00005219484,0.0002997234,0.00007675855,0.000005870696],"category_scores_gemma":[0.0001023093,0.00005326593,0.0001699748,0.0006370008,0.00006357515,0.00009111485,0.00006006752,0.0002086288,7.805875e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001548424,"about_ca_system_score_gemma":0.00002020188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007517674,"about_ca_topic_score_gemma":0.00004350963,"domain_scores_codex":[0.9990655,0.0002136974,0.0003732046,0.0001146971,0.0001168974,0.0001159948],"domain_scores_gemma":[0.9992301,0.0001339336,0.0003775432,0.0001442275,0.00009769876,0.00001646939],"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":[0.0001599873,0.0001845828,0.001267552,0.0000854377,0.001825696,0.0002010189,0.1912034,0.00001907638,0.1505828,0.004746103,0.0002183837,0.6495059],"study_design_scores_gemma":[0.02337164,0.006365337,0.6060724,0.0009896854,0.007348867,0.002285455,0.08394853,0.07033136,0.1343859,0.04713555,0.01506786,0.002697389],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5894193,0.0005097101,0.4085935,0.0004631396,0.0004896849,0.00003163897,5.610294e-7,0.00001735247,0.0004750735],"genre_scores_gemma":[0.9955591,0.00002442534,0.003595335,0.000584615,0.0001870558,8.078165e-7,4.807765e-7,0.000002779605,0.00004542137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6468086,"threshold_uncertainty_score":0.2172122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768414251105102,"score_gpt":0.3330358385620776,"score_spread":0.3153516960510265,"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."}}