{"id":"W4317910427","doi":"10.1177/20539517221149106","title":"Formally comparing topic models and human-generated qualitative coding of physician mothers’ experiences of workplace discrimination","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Human Genome Research Institute","keywords":"Coding (social sciences); Computer science; Thematic analysis; Leverage (statistics); Data science; Qualitative research; Topic model; Context (archaeology); Artificial intelligence; Sociology","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":[],"consensus_categories":[],"category_scores_codex":[0.001271993,0.00005749032,0.0001680026,0.00002938616,0.000288578,0.00002965882,0.0002406338,0.00003132535,0.000005024455],"category_scores_gemma":[0.00004887821,0.00005323977,0.00005159267,0.0005138638,0.000243473,0.0003568784,0.0001441653,0.00003971324,3.931233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001850591,"about_ca_system_score_gemma":0.00004551365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009221418,"about_ca_topic_score_gemma":0.0004596195,"domain_scores_codex":[0.999025,0.0002155369,0.0001984767,0.0001671289,0.0002786219,0.0001152428],"domain_scores_gemma":[0.9993427,0.0002568786,0.0001514437,0.0001277882,0.00009390854,0.00002724698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00000289988,0.0000269436,0.000323369,0.00003467322,0.00005952643,8.273729e-8,0.961262,0.0006737225,0.001128943,0.02511784,0.0005746231,0.01079534],"study_design_scores_gemma":[0.000161261,0.0000139187,0.002125768,0.00004498506,0.00003223593,2.285594e-8,0.8771676,0.1107249,0.0003798973,0.009074437,0.000178265,0.00009669325],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9668676,0.00008829956,0.03136003,0.0001307504,0.00006672888,0.00007635985,0.00002047775,0.0000252223,0.001364568],"genre_scores_gemma":[0.9959987,0.00006680912,0.003507771,0.0000238673,0.00007177993,0.000005304631,0.0001339004,0.000003303264,0.0001885497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1100512,"threshold_uncertainty_score":0.2219538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4102039748049899,"score_gpt":0.469404413208051,"score_spread":0.05920043840306116,"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."}}