{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000131775,0.0001929363,0.0001727572,0.0001067186,0.0002444365,0.0006152834,0.0009792477,0.00009982859,0.0002400485],"category_scores_gemma":[0.00005295697,0.000140893,0.00003904826,0.0005289527,0.00009531646,0.001316491,0.0002434354,0.0001770273,0.000354701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001448338,"about_ca_system_score_gemma":0.00001624254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003723051,"about_ca_topic_score_gemma":0.00001104226,"domain_scores_codex":[0.9984573,0.00002947259,0.0002568989,0.0004520022,0.0003994227,0.0004049177],"domain_scores_gemma":[0.999007,0.00009326028,0.0001914114,0.0005897605,0.00005150447,0.00006704285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003457177,0.0002366253,0.03897792,0.00002037519,0.0000882823,0.00001653791,0.001826358,0.000006552154,0.002996015,0.2185813,0.2739843,0.4632623],"study_design_scores_gemma":[0.005978078,0.001372954,0.01780608,0.0001943555,0.00008123826,0.0001287415,0.005976298,0.09496666,0.07479599,0.05697798,0.7370024,0.004719259],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01829816,0.0007491024,0.5361313,0.02432651,0.0005643612,0.0005728456,0.000005525602,0.005546388,0.4138058],"genre_scores_gemma":[0.9279951,0.00004348593,0.01778522,0.0003907546,0.00001834653,0.00004331938,0.000003046653,0.00001254867,0.05370818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9096969,"threshold_uncertainty_score":0.5933192,"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."}}