{"id":"W2979091142","doi":"10.5539/mas.v13n11p31","title":"Application of Naïve Bayes, Decision Tree, and K-Nearest Neighbors for Automated Text Classification","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Naive Bayes classifier; Decision tree; k-nearest neighbors algorithm; Artificial intelligence; Precision and recall; Data mining; Tree (set theory); Process (computing); Arabic; Bayes' theorem; Machine learning; The Internet; Translation (biology); Pattern recognition (psychology); Bayesian probability; Mathematics; Support vector machine; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005361391,0.001369849,0.001846023,0.008593534,0.001432429,0.001938583,0.001374822,0.001217817,0.001649656],"category_scores_gemma":[0.01332682,0.0003637584,0.001205612,0.004395498,0.0004975968,0.002652583,0.0006058095,0.0008904252,0.00106421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001459729,"about_ca_system_score_gemma":0.002398561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01770051,"about_ca_topic_score_gemma":0.01516675,"domain_scores_codex":[0.9921831,0.002294926,0.001118688,0.00125177,0.002816783,0.0003346499],"domain_scores_gemma":[0.9918207,0.004195985,0.0005923699,0.0004146505,0.002750009,0.0002263513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005047006,0.0005561052,0.01768425,0.000611816,0.0004081558,0.0002248175,0.0002871626,0.03871,0.002486401,0.004024577,0.01001516,0.9244869],"study_design_scores_gemma":[0.00008943775,0.0002439003,0.006524532,0.0001842748,0.0002107235,0.0003644927,0.0004403116,0.9667809,0.005709525,0.0113656,0.007995998,0.0000903145],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2074792,0.01300249,0.7557846,0.001824535,0.001481447,0.001172529,0.002904157,0.004196327,0.01215464],"genre_scores_gemma":[0.5089154,0.00202359,0.4818909,0.0002743541,0.0003671884,0.0003993684,0.002538235,0.00009483755,0.003496186],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01770051,"threshold_uncertainty_score":0.03519499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01284137028378582,"score_gpt":0.2646484026858366,"score_spread":0.2518070324020507,"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."}}