{"id":"W2098465658","doi":"10.1136/amiajnl-2012-001072","title":"Direct comparison between support vector machine and multinomial naive Bayes algorithms for medical abstract classification","year":2012,"lang":"en","type":"letter","venue":"Journal of the American Medical Informatics Association","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Support vector machine; Computer science; Machine learning; Naive Bayes classifier; Artificial intelligence; Algorithm; Bayesian probability; Relevance vector machine; Multinomial distribution; Task (project management); Bayes' theorem; Structured support vector machine; Data mining; Mathematics; Statistics; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06655764,0.00104431,0.002465879,0.005310845,0.0008261494,0.003956848,0.002031767,0.003656563,0.007355015],"category_scores_gemma":[0.3191024,0.0004712932,0.001614628,0.004039453,0.0008105437,0.005996997,0.001457933,0.003407169,0.004198757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002692831,"about_ca_system_score_gemma":0.00229458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001749098,"about_ca_topic_score_gemma":0.002714892,"domain_scores_codex":[0.9287969,0.04509928,0.005417681,0.003229148,0.0168854,0.000571454],"domain_scores_gemma":[0.7060374,0.253076,0.004004422,0.00763305,0.02810186,0.001147237],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005036139,0.000309562,0.007511251,0.001414747,0.0007998071,0.00008103134,0.0002131572,0.005624972,0.0007450182,0.01278597,0.02623652,0.9392419],"study_design_scores_gemma":[0.003179143,0.005962724,0.02331643,0.00357366,0.001164114,0.003182975,0.000641482,0.6612812,0.007383578,0.2188172,0.07095075,0.0005468128],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09110195,0.08209009,0.7072254,0.06710758,0.01114219,0.001763177,0.003193352,0.002766877,0.03360945],"genre_scores_gemma":[0.4645961,0.01381074,0.4932107,0.01289487,0.005379591,0.001736432,0.002780863,0.0005338396,0.005056988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9334424,"threshold_uncertainty_score":0.3519946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03009721843152888,"score_gpt":0.3180617413496284,"score_spread":0.2879645229180995,"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."}}