{"id":"W4413196475","doi":"10.2196/78082","title":"Preprocessing Large-Scale Conversational Datasets: A Framework and Its Application to Behavioral Health Transcripts","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Scale (ratio); Preprocessor; Computer science; Computational biology; Natural language processing; Psychology; Artificial intelligence; World Wide Web; Biology; Geography; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01875807,0.002525829,0.001222279,0.008832427,0.003101007,0.003884334,0.003970235,0.003301928,0.002369977],"category_scores_gemma":[0.05044506,0.0009764006,0.002855816,0.006621697,0.002294645,0.003761068,0.007174494,0.004976859,0.003657894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003108488,"about_ca_system_score_gemma":0.005375372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01331054,"about_ca_topic_score_gemma":0.01976408,"domain_scores_codex":[0.9815592,0.009036946,0.002085692,0.004031702,0.002767891,0.0005185561],"domain_scores_gemma":[0.9664358,0.0185652,0.002645566,0.005146784,0.006313063,0.0008935797],"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":[0.0007936122,0.00102576,0.01678426,0.002546083,0.0003371361,0.001319115,0.007636695,0.03734287,0.03461432,0.026305,0.05665104,0.8146442],"study_design_scores_gemma":[0.0002218852,0.0006669623,0.02491061,0.001060387,0.000252346,0.001216369,0.007360199,0.6640205,0.02929075,0.1186251,0.1519133,0.0004616297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009131718,0.0006388743,0.9639621,0.002058661,0.0001613133,0.002027216,0.01012369,0.01098811,0.0009082772],"genre_scores_gemma":[0.03283142,0.0002554765,0.9406142,0.0002929374,0.0001539113,0.003066967,0.02182261,0.0003139183,0.0006485448],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01875807,"threshold_uncertainty_score":0.09920335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1010176189570137,"score_gpt":0.5400946352524106,"score_spread":0.4390770162953969,"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."}}