{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002211452,0.0007975381,0.001463353,0.001074109,0.0005642663,0.001114026,0.001347379,0.0009124263,0.002055953],"category_scores_gemma":[0.004566588,0.0004644288,0.001490588,0.001480532,0.0004154867,0.002049497,0.001053415,0.001311984,0.001098569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005595272,"about_ca_system_score_gemma":0.0006030877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002221494,"about_ca_topic_score_gemma":0.002150608,"domain_scores_codex":[0.9989805,0.0005046419,0.00006311217,0.0001695146,0.0002040164,0.00007818088],"domain_scores_gemma":[0.9976773,0.001843702,0.00008095339,0.0001869571,0.0001782773,0.00003286358],"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":[0.0005260903,0.0002951717,0.00149469,0.0002298845,0.0002791327,0.0002001279,0.0001565619,0.3885831,0.009732528,0.013812,0.008851782,0.5758389],"study_design_scores_gemma":[0.000004965672,0.00002113082,0.0002603818,0.000004717073,0.00001305367,0.00001895743,0.000005788498,0.9903115,0.001145175,0.007872181,0.0003343356,0.000007824043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01091296,0.0004932247,0.9870602,0.0001448461,0.00005584601,0.00004624872,0.0001635683,0.0006540855,0.0004689447],"genre_scores_gemma":[0.5628306,0.0008957451,0.4258322,0.0001962161,0.0003604007,0.0004819935,0.001758064,0.0003360422,0.007308687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002221494,"threshold_uncertainty_score":0.01169538,"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."}}