{"id":"W2012971775","doi":"10.1080/0952813x.2012.721010","title":"Naive Bayes text classifiers: a locally weighted learning approach","year":2012,"lang":"en","type":"article","venue":"Journal of Experimental & Theoretical Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Naive Bayes classifier; Computer science; Artificial intelligence; Machine learning; Conditional independence; Bayes error rate; Bayesian programming; Bayes' theorem; Benchmark (surveying); Complement (music); Bayes classifier; Bayesian probability; Support vector machine; Bayes factor","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":[0.00700182,0.001987149,0.0031221,0.005481208,0.001453436,0.00289259,0.005024553,0.003028872,0.004048643],"category_scores_gemma":[0.02473951,0.0007887874,0.001564915,0.004585416,0.00134252,0.006020168,0.001807518,0.002959844,0.0033276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001463237,"about_ca_system_score_gemma":0.001818757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003620075,"about_ca_topic_score_gemma":0.004593103,"domain_scores_codex":[0.9906984,0.003562261,0.0007312726,0.001526256,0.003203726,0.0002781356],"domain_scores_gemma":[0.9893999,0.005684435,0.0007626645,0.001062913,0.002907779,0.0001823647],"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":[0.000410105,0.0003534622,0.003629642,0.0006069218,0.0003706633,0.0002041394,0.0002766852,0.07446691,0.005205722,0.01796685,0.0173277,0.8791811],"study_design_scores_gemma":[0.00009218669,0.0002029081,0.0008692876,0.0001375246,0.000182655,0.000299779,0.0001155762,0.8990396,0.004123312,0.0853314,0.009533932,0.00007193008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005819599,0.00103298,0.9888268,0.000411164,0.0001424671,0.0003434066,0.0002790961,0.001429065,0.001715448],"genre_scores_gemma":[0.1933293,0.001086913,0.7942524,0.0009873775,0.0008124894,0.00115595,0.002019601,0.0003061264,0.006049952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00700182,"threshold_uncertainty_score":0.03702956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03611338585351168,"score_gpt":0.3060859303784622,"score_spread":0.2699725445249506,"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."}}