{"id":"W2159620282","doi":"10.1142/s0218001411009019","title":"IMPACT OF TERM DEPENDENCY AND CLASS IMBALANCE ON THE PERFORMANCE OF FEATURE RANKING METHODS","year":2011,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Feature selection; Computer science; Artificial intelligence; Feature (linguistics); Univariate; Pattern recognition (psychology); Data mining; Curse of dimensionality; Machine learning; Classifier (UML); Ranking SVM; Class (philosophy); Multivariate statistics","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":[0.0004932074,0.00009012468,0.0001400329,0.0001928876,0.00003813937,0.00005319378,0.0005555524,0.00005018228,0.00006264258],"category_scores_gemma":[0.0001143297,0.00005816381,0.00007989157,0.0001102131,0.000134819,0.0003486275,0.00008489304,0.0001826458,0.000003257794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001819392,"about_ca_system_score_gemma":0.0000279536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000116997,"about_ca_topic_score_gemma":0.000002272486,"domain_scores_codex":[0.999062,0.00007476605,0.0004133065,0.0001199294,0.0002474311,0.00008253773],"domain_scores_gemma":[0.9986761,0.0001987837,0.0005794144,0.000121033,0.0003950019,0.00002971353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006653568,0.00008557869,0.01928579,0.000008128116,0.0000611202,0.000003680088,0.0007746958,0.000004443675,0.01192643,0.002984478,0.00001026562,0.9647889],"study_design_scores_gemma":[0.0001612497,0.001157283,0.14644,0.0004987808,0.00002476385,0.0001818958,0.0005340478,0.01207176,0.7718524,0.06684021,0.00002132755,0.0002162239],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7945409,0.00007331382,0.2044594,0.0004919363,0.0002350952,0.00005051043,0.000006376823,0.000009192631,0.0001332894],"genre_scores_gemma":[0.9930879,0.0003962661,0.006409822,0.00005784324,0.00003609584,0.000002012997,8.011305e-7,0.000003169701,0.000006099095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9645726,"threshold_uncertainty_score":0.2371851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1304311421720087,"score_gpt":0.3653728841263023,"score_spread":0.2349417419542936,"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."}}