{"id":"W1528447234","doi":"10.1145/563932.563930","title":"Classifying text documents by associating terms with text categories","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Categorization; Computer science; Text categorization; Association rule learning; Classifier (UML); Artificial intelligence; Text mining; Natural language processing; Information retrieval; Machine learning; Data mining","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":[0.001269478,0.0009086961,0.000881415,0.01298669,0.001018236,0.002209197,0.001007373,0.000993777,0.002425563],"category_scores_gemma":[0.006805511,0.0002043952,0.00101909,0.008686708,0.0006773715,0.003097951,0.0009225401,0.0008697693,0.002869238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005075071,"about_ca_system_score_gemma":0.0008847766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001470251,"about_ca_topic_score_gemma":0.001915609,"domain_scores_codex":[0.9986193,0.0002628947,0.0002286677,0.0002658584,0.0005233717,0.00009997378],"domain_scores_gemma":[0.9965927,0.001894401,0.0004019659,0.0002897149,0.0007147492,0.0001065816],"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":[0.0003378858,0.0005041799,0.02824619,0.00111262,0.000150192,0.0004711724,0.001097079,0.003096088,0.03532609,0.009688441,0.007814031,0.9121561],"study_design_scores_gemma":[0.0002879245,0.002605048,0.1350535,0.001730402,0.001836625,0.006552727,0.007628246,0.3856679,0.1045859,0.1871757,0.1663048,0.0005713453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3063246,0.005923875,0.6530637,0.001555034,0.0009776915,0.002241283,0.006522781,0.004413128,0.01897789],"genre_scores_gemma":[0.2982845,0.00245758,0.6858177,0.0001860166,0.0004906188,0.0008433749,0.007085952,0.0001574359,0.004676811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01298669,"threshold_uncertainty_score":0.008114278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01833621184447505,"score_gpt":0.2287015926834513,"score_spread":0.2103653808389762,"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."}}