{"id":"W1714192071","doi":"","title":"Categorical proportional difference: a feature selection method for text categorization","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Artificial intelligence; Computer science; Feature selection; Categorical variable; Word (group theory); Task (project management); Naive Bayes classifier; Mutual information; Natural language processing; Feature (linguistics); Selection (genetic algorithm); Categorization; Measure (data warehouse); Support vector machine; Pattern recognition (psychology); Machine learning; Data mining; Mathematics","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":[0.0001151066,0.0001095135,0.0001112201,0.0001295436,0.0002818085,0.00006946789,0.0003755028,0.0001291801,0.00002358722],"category_scores_gemma":[0.00008052043,0.00008428883,0.00005294949,0.00054741,0.00003550346,0.0003255774,0.00005929843,0.0001052272,0.00001996268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006985648,"about_ca_system_score_gemma":0.000118856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001455251,"about_ca_topic_score_gemma":0.000004597076,"domain_scores_codex":[0.9990567,0.00002543867,0.0001604449,0.0003514502,0.0002191942,0.0001867736],"domain_scores_gemma":[0.9994017,0.00006741799,0.00009067329,0.0002153513,0.000182845,0.00004195414],"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":[0.000006520164,0.00007506644,0.001745282,0.000006419067,0.000008574119,7.503305e-7,0.0001225459,0.00002156465,0.004967832,0.9365674,0.01275043,0.04372763],"study_design_scores_gemma":[0.00116468,0.0004855444,0.08880085,0.000004240161,0.0000181231,0.0002948736,0.0001066156,0.4773076,0.1018567,0.2797098,0.04952803,0.000722897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001269227,0.00001887073,0.9902875,0.006389541,0.0001435145,0.0003148815,8.113222e-7,0.0008499384,0.0007256875],"genre_scores_gemma":[0.5981073,0.0000144186,0.3902147,0.0001425556,0.00005386302,0.0001786432,0.00002058512,0.000005777752,0.01126218],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6568576,"threshold_uncertainty_score":0.3437199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02953612645523518,"score_gpt":0.2917414232733742,"score_spread":0.262205296818139,"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."}}