{"id":"W4402391272","doi":"10.23889/ijpds.v9i5.2864","title":"Exploring Text Classification Systems for Automatically Coding Historical Occupations and Causes of Death","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Economic and Social Research Council","keywords":"Coding (social sciences); Computer science; Natural language processing; Information retrieval; Data science; Sociology; Social science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.00355275,0.0008375276,0.0002743772,0.003135307,0.0006723218,0.001603159,0.001232194,0.0008746814,0.003163849],"category_scores_gemma":[0.01326223,0.0001994912,0.0005238021,0.002269281,0.0003380573,0.002759931,0.0009893521,0.001083647,0.001739761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00187289,"about_ca_system_score_gemma":0.001581194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02349285,"about_ca_topic_score_gemma":0.03366634,"domain_scores_codex":[0.9985649,0.0006533063,0.0001093665,0.0003177505,0.0002581592,0.00009652933],"domain_scores_gemma":[0.9912151,0.005972859,0.0005783373,0.000583188,0.001453417,0.0001971229],"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":[0.0004497745,0.001155037,0.09157407,0.000535043,0.000151638,0.0003695947,0.001934579,0.06278778,0.006217004,0.006956459,0.05121014,0.776659],"study_design_scores_gemma":[0.00007831906,0.0002184167,0.02023887,0.000153209,0.00007506794,0.0001135952,0.001695352,0.9342946,0.008859804,0.01141476,0.02280478,0.00005318699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5845052,0.001452281,0.3639387,0.005947507,0.0004996965,0.001021121,0.01859385,0.01159117,0.01245059],"genre_scores_gemma":[0.6658837,0.0004860923,0.2933542,0.0004149774,0.0001624316,0.0006180666,0.03261635,0.000182199,0.006281959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02349285,"threshold_uncertainty_score":0.04671222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5370092133463087,"score_gpt":0.5151466273038554,"score_spread":0.02186258604245328,"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."}}