{"id":"W2128866918","doi":"10.1109/icsmc.2007.4414080","title":"Combining feature ranking for text classification","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Ranking (information retrieval); Pattern recognition (psychology); Classifier (UML); Feature (linguistics); Curse of dimensionality; Majority rule; Dimensionality reduction; Support vector machine; Ranking SVM; Data mining; Feature extraction; Feature vector; Machine learning; Feature selection","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":[0.003201641,0.001565333,0.002057677,0.004480279,0.0006506323,0.001302477,0.0008569501,0.0007339078,0.002308264],"category_scores_gemma":[0.006966484,0.000315708,0.001711946,0.004587094,0.0004100064,0.001980043,0.0007313229,0.0007874086,0.002061254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004043312,"about_ca_system_score_gemma":0.000528071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001171704,"about_ca_topic_score_gemma":0.001704242,"domain_scores_codex":[0.9960021,0.00131643,0.00027582,0.0005472168,0.001635337,0.0002230723],"domain_scores_gemma":[0.9966224,0.00159226,0.0002767334,0.0004439701,0.0009886925,0.00007592785],"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":[0.0001759182,0.0001232325,0.002409432,0.0002200908,0.000235953,0.00008969485,0.00006008771,0.02021246,0.01664732,0.001835521,0.00507266,0.9529176],"study_design_scores_gemma":[0.00009248187,0.00105584,0.01245018,0.00006568568,0.0004436247,0.0008078171,0.0001772255,0.9018812,0.04292249,0.02225663,0.0176206,0.0002263252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0274615,0.00135563,0.9664155,0.0001319865,0.0001278479,0.0001893866,0.0003041377,0.001875706,0.002138301],"genre_scores_gemma":[0.3742747,0.0007968639,0.6202052,0.0001131112,0.0002783257,0.0003691915,0.001432159,0.0001816699,0.002348748],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004480279,"threshold_uncertainty_score":0.01693213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03615333796315819,"score_gpt":0.298108691432085,"score_spread":0.2619553534689268,"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."}}