{"id":"W4245824053","doi":"10.1007/978-3-540-68636-1_62","title":"Maximum Entropy Modeling with Feature Selection for Text Categorization","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Categorization; Principle of maximum entropy; Text categorization; Computer science; Artificial intelligence; Entropy (arrow of time); Pattern recognition (psychology); Feature (linguistics); Selection (genetic algorithm); Data mining; Machine learning; Natural language processing","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"],"consensus_categories":[],"category_scores_codex":[0.0002356978,0.0004305859,0.0003495031,0.000801748,0.0004288919,0.0004630553,0.001850531,0.000391934,0.000004568636],"category_scores_gemma":[0.00004920724,0.0003546118,0.00008290538,0.0007431295,0.0003135855,0.000817481,0.0003232233,0.0005327918,0.00001130339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003462768,"about_ca_system_score_gemma":0.0004603268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009668761,"about_ca_topic_score_gemma":0.00003696036,"domain_scores_codex":[0.9972097,0.00001184537,0.0003115142,0.001299149,0.0006624624,0.0005053359],"domain_scores_gemma":[0.998315,0.0001303445,0.0002661474,0.0008027665,0.0004076447,0.00007813687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002809788,0.00003885617,0.00009045877,0.00004843606,0.00001813225,0.000009660719,0.0006110073,0.2345497,0.0004519168,0.1208743,0.0002361738,0.6430433],"study_design_scores_gemma":[0.0002875994,0.0002261357,0.00001292033,0.00008452001,0.000006732833,0.00005948268,2.901019e-7,0.8805625,0.002188951,0.1137292,0.002402408,0.0004393157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005573432,0.0002608563,0.9957011,0.001806287,0.0005420227,0.0006485794,0.000002714422,0.0005505344,0.0004321745],"genre_scores_gemma":[0.201395,0.0001624803,0.7968208,0.0004464325,0.0003002494,0.00005936174,0.00002249144,0.00004424938,0.000748964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6460127,"threshold_uncertainty_score":0.9998906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01838609183178649,"score_gpt":0.2334559349983046,"score_spread":0.2150698431665181,"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."}}