{"id":"W1595744771","doi":"10.5555/1786374.1786451","title":"Maximum entropy modeling with feature selection for text categorization","year":2008,"lang":"en","type":"article","venue":"Asia Information Retrieval Symposium","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Feature selection; Principle of maximum entropy; Categorization; Computer science; Text categorization; Artificial intelligence; Entropy (arrow of time); Pattern recognition (psychology); Feature (linguistics); Selection (genetic algorithm); Cross entropy; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000130898,0.0001562373,0.0001277744,0.0002520504,0.0004009016,0.0002309423,0.0004013902,0.0001541683,0.000005168443],"category_scores_gemma":[0.00005007294,0.0001310079,0.00004905797,0.0008356893,0.00003504698,0.003875086,0.00005023577,0.0001341768,0.00005178014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001290202,"about_ca_system_score_gemma":0.0001208829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001061292,"about_ca_topic_score_gemma":0.000001508136,"domain_scores_codex":[0.9988998,0.00001470222,0.0002917004,0.0001913494,0.000354767,0.000247751],"domain_scores_gemma":[0.9989978,0.00002780875,0.0002206753,0.0002872616,0.000411902,0.00005453389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005332652,0.0001303099,0.003252183,0.0001383369,0.00009597261,0.00000151544,0.004551294,0.03953542,0.01066127,0.9106379,0.01122678,0.01923572],"study_design_scores_gemma":[0.001032251,0.000361516,0.0004942702,0.00001223605,0.00001324751,0.00007204631,0.0001554916,0.9336566,0.03569757,0.002988543,0.02518777,0.000328402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01037799,0.00001378169,0.9818545,0.004810885,0.0001912767,0.000564802,0.0000033735,0.0007807525,0.001402674],"genre_scores_gemma":[0.9662746,0.00006865824,0.0329139,0.0001913045,0.00004968364,0.00005880694,0.0001028556,0.000008945204,0.0003313079],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558966,"threshold_uncertainty_score":0.5342345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01148243115622647,"score_gpt":0.2143680934824013,"score_spread":0.2028856623261748,"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."}}