{"id":"W4213136595","doi":"10.31234/osf.io/bwp3t","title":"PassivePy: A Tool to Automatically Identify Passive Voice in Big Text Data","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Mental Health via Writing","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Construct (python library); Passive voice; Field (mathematics); Construal level theory; Overhead (engineering); Scale (ratio); Speech recognition; Natural language processing; Human–computer interaction; Psychology; Linguistics; Social psychology","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":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001553722,0.0004972855,0.0008025587,0.0005535157,0.0001663914,0.0001541729,0.002981407,0.000458944,0.02506797],"category_scores_gemma":[0.0006495258,0.000535117,0.0001015331,0.0005523836,0.00005522466,0.0001029337,0.01269295,0.002127369,0.004966072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007390465,"about_ca_system_score_gemma":0.0004807287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004614312,"about_ca_topic_score_gemma":0.001969111,"domain_scores_codex":[0.9937379,0.0008226192,0.001555561,0.002099134,0.0007551593,0.00102957],"domain_scores_gemma":[0.9943462,0.0007457534,0.0004402566,0.004063331,0.00007221927,0.0003322102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004090431,0.002111558,0.0169047,0.002715411,0.0004697964,0.002720146,0.01031565,0.000154253,0.0001886536,0.02197976,0.4125421,0.5294889],"study_design_scores_gemma":[0.004103546,0.0005869709,0.6929374,0.00191362,0.000212604,0.0001810745,0.02134801,0.005671341,0.00004794951,0.008090601,0.2614013,0.003505637],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6539642,0.0004456949,0.006213911,0.02109509,0.01604479,0.009080531,0.002875662,0.00109689,0.2891832],"genre_scores_gemma":[0.9108526,0.00003164339,0.02539504,0.02042122,0.001461228,0.006032611,0.002997154,0.0003110934,0.03249746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6760327,"threshold_uncertainty_score":0.99971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1190872482535212,"score_gpt":0.448682014027452,"score_spread":0.3295947657739308,"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."}}