{"id":"W49807964","doi":"","title":"A simple feature selection method for text classification","year":2001,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Computer science; Information gain; Feature (linguistics); Simple (philosophy); Set (abstract data type); Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Data mining; Feature extraction; Machine learning","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":[0.0004294358,0.0002243549,0.0001898155,0.0003890519,0.0002160705,0.0005579018,0.001211665,0.0001662892,0.0002508794],"category_scores_gemma":[0.0004357975,0.0002130757,0.0001310681,0.0005185675,0.00007544675,0.000615337,0.0001189899,0.0002535256,0.0003496277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001763135,"about_ca_system_score_gemma":0.0001081762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003000382,"about_ca_topic_score_gemma":0.00005887542,"domain_scores_codex":[0.9980019,0.00006280678,0.0004736558,0.0006989729,0.0004494225,0.0003132412],"domain_scores_gemma":[0.9982961,0.0002062664,0.0002849587,0.0004565737,0.0006754443,0.00008068897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000318615,0.00008534625,0.00005186684,0.000002036264,0.00001337399,0.000001070502,0.00007666352,0.0001168624,0.0157699,0.6268655,0.001189392,0.3557961],"study_design_scores_gemma":[0.00004645118,0.0001492551,0.0007683095,0.00001948851,0.000004662375,0.00001413243,0.0002564202,0.546196,0.06476967,0.3614761,0.02607468,0.0002247993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009265626,0.000008568831,0.9591491,0.0315516,0.0006988092,0.0004118876,0.00001064887,0.00055733,0.006685445],"genre_scores_gemma":[0.8898557,0.00006470622,0.1076037,0.0006159761,0.0001813968,0.0002411114,0.00003488724,0.00001362386,0.001388859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8889292,"threshold_uncertainty_score":0.8688976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1510900227271396,"score_gpt":0.3835078255874474,"score_spread":0.2324178028603078,"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."}}