{"id":"W2089870669","doi":"10.1016/j.eswa.2011.09.160","title":"Comparison of term frequency and document frequency based feature selection metrics in text categorization","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Faculty of Graduate Studies and Research, University of Alberta; Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Feature selection; Discriminative model; Computer science; Term (time); Text categorization; Categorization; Word lists by frequency; Feature (linguistics); Frequency; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); tf–idf; Data mining; Mathematics; Statistics","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":[0.0001451599,0.0001449336,0.0002187988,0.0004319269,0.0001083949,0.00007278683,0.0004383797,0.0001207827,0.000006395428],"category_scores_gemma":[0.00001616889,0.0001201902,0.00001915196,0.001553678,0.00006929315,0.0004054891,0.00003889412,0.0001189491,0.00000599574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103373,"about_ca_system_score_gemma":0.00007483242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003874626,"about_ca_topic_score_gemma":0.00004635248,"domain_scores_codex":[0.998818,0.00004818357,0.0003624511,0.0003779054,0.0002285486,0.0001649525],"domain_scores_gemma":[0.9989477,0.00004931776,0.0003041427,0.0004997521,0.0001482781,0.00005084547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00000663657,0.000301439,0.3544643,0.00008507377,0.00002143912,6.614484e-7,0.002562189,0.00003322574,0.009819295,0.6222152,0.000515205,0.009975277],"study_design_scores_gemma":[0.005529375,0.001854689,0.6391277,0.0006298409,0.0001000628,0.00007703797,0.007982855,0.09260122,0.1881626,0.04686606,0.01386802,0.003200532],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004883914,0.001507407,0.9900603,0.0004039295,0.00005503541,0.0009927601,0.000002316281,0.0003044728,0.001789862],"genre_scores_gemma":[0.9390606,0.00003145553,0.0596256,0.00001939772,0.00001459754,0.001170222,0.00001352673,0.000009036117,0.00005551413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9341767,"threshold_uncertainty_score":0.4901213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03104747594243825,"score_gpt":0.2863871260576094,"score_spread":0.2553396501151711,"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."}}