{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002278403,0.001651373,0.002019338,0.003022626,0.0009101505,0.00107601,0.001194247,0.001332577,0.004820641],"category_scores_gemma":[0.006156411,0.0003193792,0.001582974,0.003925041,0.0005095998,0.001469815,0.0007955912,0.0009734111,0.003160294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004149337,"about_ca_system_score_gemma":0.0007573023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001470541,"about_ca_topic_score_gemma":0.001394637,"domain_scores_codex":[0.9971007,0.000722519,0.0002365316,0.0005252296,0.001292128,0.0001229094],"domain_scores_gemma":[0.9979283,0.001051132,0.0001157213,0.0002287362,0.0006250978,0.00005101961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002489852,0.0001660993,0.001129406,0.0002850081,0.000159847,0.0001447241,0.00007858877,0.009971893,0.0203154,0.002003688,0.0086727,0.9568236],"study_design_scores_gemma":[0.0005533823,0.001512734,0.01445585,0.0001822656,0.0004831048,0.002662949,0.0001805051,0.7893302,0.08213478,0.02697795,0.08112256,0.0004037596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008176571,0.0006047228,0.9860548,0.0001626072,0.0002029307,0.000689494,0.0006146905,0.002649612,0.0008446968],"genre_scores_gemma":[0.07247215,0.0004311839,0.9202034,0.0001619129,0.0002463771,0.00141054,0.001618347,0.0001887184,0.00326735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004820641,"threshold_uncertainty_score":0.01612669,"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."}}