{"id":"W1968377807","doi":"10.1080/13645579.2011.645700","title":"A computer-assisted approach to filtering large numbers of documents for media analyses","year":2012,"lang":"en","type":"article","venue":"International Journal of Social Research Methodology","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Trinity Western University; Western University; Abbotsford Veterinary Clinic","funders":"Trinity Western University","keywords":"Computer science; Selection (genetic algorithm); Filter (signal processing); Selection bias; Information retrieval; Reduction (mathematics); Data mining; Data science; Machine learning; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.01482768,0.001727318,0.002397231,0.01781333,0.002471493,0.004302418,0.00202702,0.002092079,0.01050788],"category_scores_gemma":[0.04214191,0.0009577386,0.001460665,0.01242811,0.0007908195,0.003529375,0.00270546,0.001654204,0.006859697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007218812,"about_ca_system_score_gemma":0.002565702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0038045,"about_ca_topic_score_gemma":0.00685765,"domain_scores_codex":[0.9901885,0.002941701,0.001477801,0.002028737,0.003082052,0.0002811368],"domain_scores_gemma":[0.9375458,0.04248341,0.003393296,0.005647536,0.01010556,0.0008243469],"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":[0.0006996467,0.0005425259,0.005749843,0.0007726457,0.0004006444,0.0003032295,0.001579224,0.002778615,0.04775783,0.002800014,0.0222188,0.9143971],"study_design_scores_gemma":[0.0009224784,0.001323974,0.0327448,0.0004611521,0.001202805,0.003264823,0.002225233,0.6034699,0.132964,0.03455442,0.1860829,0.0007836027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01502607,0.0005439094,0.9449423,0.0004475003,0.0001867283,0.002113743,0.00194281,0.03290827,0.001888659],"genre_scores_gemma":[0.037492,0.0001894664,0.9567405,0.0001727019,0.0002678706,0.001310087,0.001399166,0.0004324779,0.00199576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01781333,"threshold_uncertainty_score":0.07841724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6865705192359098,"score_gpt":0.610141181123146,"score_spread":0.07642933811276387,"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."}}