{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009144688,0.0002396505,0.0003270722,0.0002373482,0.0002104802,0.0002729346,0.00129126,0.0001748619,0.000334693],"category_scores_gemma":[0.0002728032,0.0001832922,0.0002104095,0.0005143788,0.0008898595,0.001155233,0.0003285641,0.0006530599,0.0001733914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372996,"about_ca_system_score_gemma":0.00006618175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001892644,"about_ca_topic_score_gemma":6.110972e-8,"domain_scores_codex":[0.9974698,0.0002028163,0.0008520248,0.0002797174,0.0006692237,0.0005264455],"domain_scores_gemma":[0.998501,0.0002479359,0.0004200476,0.0003423505,0.0002055335,0.0002831216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008547059,0.0006060054,0.00008845663,0.000003448251,0.0000280587,0.000006149906,0.001583429,0.00002433447,0.02626935,0.9285442,0.00009306895,0.04266809],"study_design_scores_gemma":[0.00008786885,0.0007957029,0.00003389224,0.00003979126,0.00001526116,0.0001254545,0.007202719,0.02843588,0.781793,0.1800135,0.001139314,0.0003176664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0531248,0.001223829,0.9367777,0.0009313916,0.0006039502,0.0001450908,4.246142e-7,0.0001577846,0.007035095],"genre_scores_gemma":[0.9550135,0.00004376105,0.04449932,0.0001358083,0.0002338697,0.0000109438,8.113285e-7,0.00001443847,0.00004756886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9018887,"threshold_uncertainty_score":0.7474439,"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."}}