{"id":"W4386869826","doi":"10.2139/ssrn.4568851","title":"Cognitive Biases in Natural Language: Automatically Detecting, Differentiating, and Measuring Bias in Text","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Natural (archaeology); Computer science; Natural language processing; Cognitive bias; Cognition; Cognitive psychology; Natural language; Natural language understanding; Artificial intelligence; Psychology; Linguistics; Philosophy; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004158855,0.0006535956,0.000873121,0.003677597,0.0004073016,0.003536004,0.0008373588,0.001315511,0.002033946],"category_scores_gemma":[0.05718878,0.0003565579,0.0004834282,0.002013318,0.0006982773,0.004357826,0.001483219,0.001203311,0.001420984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005212051,"about_ca_system_score_gemma":0.0008344484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001365054,"about_ca_topic_score_gemma":0.001642365,"domain_scores_codex":[0.9959116,0.001229801,0.000454649,0.001046059,0.001147235,0.0002106465],"domain_scores_gemma":[0.9372093,0.04838829,0.006672163,0.002453908,0.004312745,0.0009636021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002230475,0.0006494718,0.1312228,0.001498896,0.0003527529,0.0003512175,0.003985253,0.002138279,0.1246178,0.003010485,0.006336797,0.7236058],"study_design_scores_gemma":[0.0005532908,0.001906449,0.460124,0.0005563846,0.001284599,0.002745781,0.005260943,0.2819088,0.1655008,0.06563654,0.01399439,0.0005280776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8733392,0.001676736,0.1144343,0.0006322828,0.0002084003,0.0003440617,0.001718173,0.002911285,0.004735457],"genre_scores_gemma":[0.9277915,0.0003878763,0.06876288,0.0002496875,0.0001942292,0.000182279,0.001375084,0.0002244254,0.0008320956],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004158855,"threshold_uncertainty_score":0.02199441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04473239820399759,"score_gpt":0.3088940874624128,"score_spread":0.2641616892584152,"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."}}