{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004275457,0.0004167155,0.0003342142,0.000810865,0.000338848,0.001079387,0.0019822,0.0004907637,0.000009686974],"category_scores_gemma":[0.00008289864,0.0003809681,0.0001022517,0.0007891048,0.0003640897,0.001165555,0.0002784313,0.0005086085,0.00001730028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003122049,"about_ca_system_score_gemma":0.0005656017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004119874,"about_ca_topic_score_gemma":0.00003847121,"domain_scores_codex":[0.997418,0.00001787801,0.0002953478,0.001247624,0.0005337835,0.0004873807],"domain_scores_gemma":[0.9982501,0.0002074944,0.0003019304,0.0008295058,0.0003416091,0.00006934546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003438444,0.000016466,0.00002315113,0.00003387323,0.000006850931,0.000002293169,0.000207915,0.00684462,0.0004442736,0.6106219,0.0007038043,0.3810914],"study_design_scores_gemma":[0.0002589671,0.0002108866,0.00005062897,0.0000778157,0.000008246497,0.00002646305,0.000001099159,0.1731184,0.00481138,0.7912964,0.02952479,0.0006149675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001022032,0.0002910671,0.9914142,0.003683981,0.001215873,0.0005955395,0.000003350098,0.000498282,0.002287447],"genre_scores_gemma":[0.09378729,0.0001003339,0.9001791,0.001651051,0.0003712694,0.00009519058,0.00002717819,0.00005656149,0.003732013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3804765,"threshold_uncertainty_score":0.9999576,"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."}}