{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01062772,0.00008400418,0.0003321187,0.0006221834,0.00008713613,0.0000635813,0.001606617,0.00008403468,0.0000157233],"category_scores_gemma":[0.002522102,0.00007541195,0.0001854649,0.0003031588,0.000064702,0.0004291333,0.0005649699,0.0002883021,0.000002719384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001748402,"about_ca_system_score_gemma":0.0001463367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004929316,"about_ca_topic_score_gemma":0.000004675806,"domain_scores_codex":[0.996426,0.00132078,0.0005613751,0.0001638961,0.001090864,0.0004370812],"domain_scores_gemma":[0.9950816,0.002776235,0.0002994064,0.000131478,0.001540855,0.0001704327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009025877,0.00168516,0.003639311,0.0001259507,0.002099005,0.00003729387,0.07262011,0.001549406,0.06455043,0.5271019,0.007145564,0.3185433],"study_design_scores_gemma":[0.02929923,0.004300952,0.2338042,0.0009475632,0.000388643,0.002320854,0.02472624,0.269429,0.1054426,0.2031111,0.1231257,0.003104013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04845785,0.00006222348,0.9482179,0.001208665,0.001405011,0.0001094151,0.000008288714,0.000007197288,0.0005234557],"genre_scores_gemma":[0.4472004,0.000005023897,0.5518031,0.00008349541,0.0008744931,0.000006554593,0.000001484392,0.000004900792,0.0000206221],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3987425,"threshold_uncertainty_score":0.3683377,"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."}}