{"id":"W1960913922","doi":"10.1007/3-540-44886-1_41","title":"Feature Selection Strategies for Text Categorization","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Categorization; Computer science; Selection (genetic algorithm); Text categorization; Feature (linguistics); Rank (graph theory); Artificial intelligence; Set (abstract data type); Filter (signal processing); Function (biology); Representation (politics); Machine learning; Data mining; Pattern recognition (psychology); Mathematics","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":[0.001643236,0.0009862849,0.001322434,0.002467728,0.0007472325,0.001281381,0.001686222,0.0008831742,0.004477978],"category_scores_gemma":[0.00348859,0.0003949352,0.0009094627,0.002632889,0.0003853787,0.001821872,0.0008740416,0.0009872472,0.002495321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003834056,"about_ca_system_score_gemma":0.0006250866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001972272,"about_ca_topic_score_gemma":0.002656563,"domain_scores_codex":[0.9992136,0.0002337535,0.00009495334,0.0001552819,0.0002283412,0.00007403511],"domain_scores_gemma":[0.9982754,0.001000469,0.00006025261,0.0002014834,0.0004116729,0.0000507922],"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":[0.0001587807,0.0001144039,0.0004653648,0.0001160476,0.00005772994,0.00007733833,0.00007926731,0.005447129,0.009766662,0.003072864,0.009604596,0.9710397],"study_design_scores_gemma":[0.0002283097,0.0004439759,0.004419132,0.0001057735,0.0002889644,0.000740144,0.0003157842,0.8501797,0.03715748,0.08321512,0.022817,0.00008865974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01752741,0.002686456,0.9744018,0.0002294571,0.0001670631,0.0001775198,0.0004362455,0.002417955,0.00195606],"genre_scores_gemma":[0.1952155,0.001547232,0.7884749,0.0002622606,0.0003760878,0.0005928451,0.003174931,0.0004473863,0.009908844],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004477978,"threshold_uncertainty_score":0.01498032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01843416811592578,"score_gpt":0.2540111248480112,"score_spread":0.2355769567320854,"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."}}