{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004642471,0.00007963039,0.00007834437,0.0001357156,0.0001570213,0.0001490837,0.000622437,0.00009258032,0.000007448074],"category_scores_gemma":[0.00007691291,0.00006784799,0.00004434246,0.0003265921,0.00003115995,0.0003863183,0.00007523101,0.00008226436,0.00002965184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003562095,"about_ca_system_score_gemma":0.00001754353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001511454,"about_ca_topic_score_gemma":0.000004338148,"domain_scores_codex":[0.9992332,0.000006586053,0.0001504557,0.0002555924,0.0001364644,0.0002177225],"domain_scores_gemma":[0.9992124,0.0001782123,0.00008584691,0.0004169989,0.00007483661,0.00003166176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003108703,0.00001431663,0.0004457515,0.000003199541,0.00000308776,2.30365e-7,0.00009306753,5.462815e-7,0.005877854,0.7755054,0.004882429,0.213171],"study_design_scores_gemma":[0.002259796,0.0002569486,0.08100662,0.00004043704,0.00001530697,0.00001670228,0.001935966,0.06509753,0.1700776,0.1701538,0.5082785,0.0008608589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001945666,0.0000540817,0.9733363,0.007313573,0.0002229802,0.0002061587,3.111132e-7,0.0009857193,0.01593526],"genre_scores_gemma":[0.8122765,0.000004265878,0.1848778,0.0002880887,0.0000257245,0.0000210946,0.000003794277,0.000004649598,0.002498082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8103308,"threshold_uncertainty_score":0.2766761,"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."}}