{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007369473,0.0007362022,0.001714788,0.008694715,0.0006183662,0.002287736,0.0008298984,0.001058735,0.0009872641],"category_scores_gemma":[0.02153089,0.000160184,0.0009252518,0.006065359,0.0003891039,0.003035834,0.0007324978,0.0007328248,0.0004117906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009292995,"about_ca_system_score_gemma":0.001007283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002635662,"about_ca_topic_score_gemma":0.003027074,"domain_scores_codex":[0.9952807,0.001381554,0.0006418823,0.000368515,0.002099152,0.0002282765],"domain_scores_gemma":[0.9680778,0.02402744,0.001336264,0.0008269638,0.0051425,0.0005889791],"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":[0.003741232,0.0007666025,0.04127194,0.001211128,0.0008361935,0.0001132483,0.0003835254,0.01296392,0.01714732,0.002503321,0.006852606,0.9122091],"study_design_scores_gemma":[0.0006886059,0.006505141,0.2174399,0.0003248268,0.001431435,0.001343719,0.001517268,0.7219796,0.0291134,0.009271628,0.009999031,0.0003855258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8060538,0.01900421,0.1651201,0.0008211363,0.0005060783,0.0003177764,0.002392485,0.001909372,0.003874871],"genre_scores_gemma":[0.8899647,0.002226198,0.1014041,0.00009452019,0.0003152272,0.000222533,0.003983019,0.0001574125,0.001632305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008694715,"threshold_uncertainty_score":0.03897399,"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."}}