{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004847405,0.0004024921,0.0004385223,0.001082544,0.0002495992,0.0003151105,0.002375111,0.0004179574,0.000004293096],"category_scores_gemma":[0.0000724123,0.000349276,0.00008134804,0.0008728459,0.0002250867,0.000599707,0.0002040706,0.000542177,0.000005783033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002553503,"about_ca_system_score_gemma":0.000315178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001366397,"about_ca_topic_score_gemma":0.00008386292,"domain_scores_codex":[0.9970555,0.00003992195,0.0004348184,0.001348745,0.0007429468,0.000378066],"domain_scores_gemma":[0.9977625,0.0002306985,0.0003989752,0.001166513,0.000358666,0.00008262102],"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":[0.00002385334,0.0004078437,0.0004688441,0.00002284894,0.000009852979,0.000003141673,0.001382661,0.01143846,0.000435712,0.03527312,0.0001391909,0.9503945],"study_design_scores_gemma":[0.001259675,0.009320344,0.005519224,0.0001535209,0.00003248804,0.00002182687,0.000006640321,0.495672,0.01103047,0.4731877,0.002558804,0.001237296],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001318029,0.00006126484,0.9952554,0.001016523,0.0005331772,0.0009945788,0.000002278807,0.0003568803,0.0004619096],"genre_scores_gemma":[0.8961018,0.00001260144,0.1027554,0.0004921725,0.0001927701,0.00003332501,0.00001335021,0.00002371072,0.0003749628],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9491572,"threshold_uncertainty_score":0.9998959,"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."}}