{"id":"W2000918452","doi":"10.1145/1281192.1281260","title":"A concept-based model for enhancing text categorization","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Categorization; Sentence; Artificial intelligence; Phrase; Term (time); Weighting; Graph; Information retrieval; Theoretical computer science","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":[0.002313172,0.001244986,0.0006617145,0.003740012,0.0007282894,0.001664525,0.002314668,0.001192433,0.003666173],"category_scores_gemma":[0.007057735,0.0003522958,0.001326572,0.00341783,0.0007239598,0.004648527,0.001177576,0.001542793,0.00168244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681884,"about_ca_system_score_gemma":0.002022671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006619163,"about_ca_topic_score_gemma":0.005640667,"domain_scores_codex":[0.9982322,0.0004046697,0.0001125968,0.0004109778,0.0007659274,0.00007378394],"domain_scores_gemma":[0.9977648,0.001174707,0.0001220963,0.0001925168,0.0006892347,0.00005650875],"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":[0.0003021224,0.0004592792,0.002476509,0.0007628257,0.0001967264,0.0003268193,0.0009649023,0.069766,0.01919918,0.108221,0.01414671,0.7831779],"study_design_scores_gemma":[0.00004167233,0.0001371727,0.001150161,0.00008617753,0.00009389679,0.0003372068,0.0001487144,0.9024665,0.005554552,0.06749175,0.02243443,0.00005765586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006018725,0.0003177314,0.9897192,0.0002867509,0.00008181383,0.0004144969,0.0003569523,0.001070405,0.001733999],"genre_scores_gemma":[0.1037561,0.0004685099,0.8906437,0.0002651718,0.00009284219,0.001050457,0.0009986327,0.0001004563,0.002624123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006619163,"threshold_uncertainty_score":0.01316124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02597749126124376,"score_gpt":0.281605414501903,"score_spread":0.2556279232406592,"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."}}