{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1116912,0.0007794771,0.0006169264,0.002912056,0.00154069,0.006772721,0.003183432,0.001750388,0.004091344],"category_scores_gemma":[0.4052806,0.0007219624,0.00147213,0.002903856,0.006000617,0.006448964,0.004291059,0.002529687,0.0005715975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006786175,"about_ca_system_score_gemma":0.00589964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005503365,"about_ca_topic_score_gemma":0.006189561,"domain_scores_codex":[0.8477873,0.1369834,0.003519475,0.004960452,0.006008444,0.0007409418],"domain_scores_gemma":[0.2967157,0.6607538,0.01414245,0.01964381,0.007960765,0.0007833885],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001204097,0.0006768336,0.06607608,0.00411088,0.0007068086,0.0004262227,0.1797377,0.1392483,0.003802149,0.4404224,0.007969051,0.1556196],"study_design_scores_gemma":[0.000408226,0.0003648929,0.01671957,0.001700012,0.0001576551,0.0002783891,0.03754101,0.5168979,0.004669337,0.3981003,0.02288653,0.0002760807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1155023,0.0002540163,0.8711876,0.00298041,0.0001305176,0.001898286,0.001539764,0.0003900952,0.006117],"genre_scores_gemma":[0.5983464,0.0001295785,0.3927039,0.0005076421,0.00005972419,0.005834904,0.001574032,0.0001562036,0.0006877193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8883088,"threshold_uncertainty_score":0.5906863,"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."}}