{"id":"W2117423052","doi":"10.1109/icdm.2002.1183881","title":"Text document categorization by term association","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Classifier (UML); Categorization; Artificial intelligence; Text categorization; Association rule learning; Machine learning; Natural language processing; Data mining; Information retrieval; Pattern recognition (psychology)","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":[0.0001915998,0.00005133496,0.00004523106,0.00002156379,0.00008781657,0.0001910437,0.0002321062,0.0000293387,0.0000604623],"category_scores_gemma":[0.00003164484,0.00004650152,0.00001383349,0.0002169256,0.000003615588,0.0003815386,0.0000312744,0.00003466696,0.000202703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008327157,"about_ca_system_score_gemma":0.00002314516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002378188,"about_ca_topic_score_gemma":0.00000201044,"domain_scores_codex":[0.9994141,0.00002268918,0.0001050389,0.0001837376,0.0001502354,0.0001242326],"domain_scores_gemma":[0.999586,0.00002928058,0.00005825962,0.0002478363,0.00003867842,0.00003987605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[1.1904e-7,0.00007681376,0.001755596,0.00000194379,0.00001159404,2.812368e-7,0.0001798778,0.00000691664,0.001901452,0.7541828,0.1497347,0.09214789],"study_design_scores_gemma":[0.0005734193,0.00006589701,0.003700466,0.000005795639,0.00001193819,0.000005494903,0.00005637317,0.02319917,0.03620964,0.01985304,0.9158555,0.0004632351],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009139549,0.000019547,0.9739731,0.001031761,0.0001217167,0.00007570568,0.00000369152,0.0001184295,0.02374212],"genre_scores_gemma":[0.5951189,0.00006771811,0.3447198,0.001356419,0.00007062284,0.000129567,0.0001525599,0.00001602137,0.05836838],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7661209,"threshold_uncertainty_score":0.2605405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005463032048834978,"score_gpt":0.2254333012677956,"score_spread":0.2199702692189607,"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."}}