{"id":"W1524564918","doi":"10.1007/978-3-642-01818-3_35","title":"An Empirical Study of Category Skew on Feature Selection for Text Categorization","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Skew; Categorical variable; Feature selection; Computer science; Categorization; Text categorization; Selection (genetic algorithm); Feature (linguistics); Measure (data warehouse); Artificial intelligence; Pattern recognition (psychology); Data mining; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01808162,0.0003563265,0.0005248297,0.001042546,0.0006161046,0.001092594,0.0006996559,0.0006472835,0.002276292],"category_scores_gemma":[0.1369886,0.0001692043,0.0004513205,0.001773221,0.001072006,0.002849672,0.001098984,0.001148135,0.0004527857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006092974,"about_ca_system_score_gemma":0.0004152006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009279626,"about_ca_topic_score_gemma":0.0009283031,"domain_scores_codex":[0.9911117,0.005661095,0.0004400625,0.0007877692,0.001725305,0.0002739654],"domain_scores_gemma":[0.6219091,0.3391264,0.01302478,0.01528933,0.009133244,0.001517141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005324094,0.001088062,0.7385889,0.0003034551,0.0004531299,0.0002221925,0.001483682,0.01133716,0.008818304,0.00310011,0.005423759,0.2238572],"study_design_scores_gemma":[0.0001876919,0.002625991,0.7992706,0.000134198,0.0003533077,0.001572487,0.002567997,0.1678899,0.008927122,0.01383545,0.002510739,0.000124505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912608,0.0004110477,0.006793922,0.0001100117,0.00003204964,0.00002716808,0.0002087009,0.0000596616,0.001096709],"genre_scores_gemma":[0.9969939,0.00005547047,0.002123388,0.00003045558,0.00002729927,0.00001330493,0.0004549706,0.00002319972,0.0002779781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01808162,"threshold_uncertainty_score":0.09562588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02664566840595388,"score_gpt":0.3034475151411274,"score_spread":0.2768018467351735,"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."}}