{"id":"W4388474969","doi":"10.18280/ria.370515","title":"Using Natural Language Processing for Programming Language Code Classification with Multinomial Naive Bayes","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Multinomial distribution; Naive Bayes classifier; Artificial intelligence; Code (set theory); Programming language; Statistics; Mathematics; Support vector machine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005002192,0.0001682017,0.0001655651,0.0001756159,0.0002504236,0.0002846467,0.000655774,0.00006415071,0.000004642334],"category_scores_gemma":[0.0005697848,0.0001521032,0.00006157692,0.001218225,0.00006994,0.0003810394,0.0001354799,0.0002097954,0.00006723605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021848,"about_ca_system_score_gemma":0.00008173176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003632152,"about_ca_topic_score_gemma":0.00001836828,"domain_scores_codex":[0.9983713,0.0000322095,0.0002618516,0.0005320944,0.000260889,0.0005416453],"domain_scores_gemma":[0.9986491,0.0005263072,0.00009580421,0.0004693036,0.0001734306,0.00008608215],"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":[0.00003676681,0.00006879039,0.00104027,0.0003371602,0.00002137454,0.00006360329,0.01820726,0.04428883,0.04262835,0.0005791743,0.00008068447,0.8926477],"study_design_scores_gemma":[0.00006444495,0.00006096841,0.000281635,0.0001393126,0.000005499146,0.00002605309,0.003033036,0.9561221,0.03951066,0.00001316095,0.0005364873,0.0002066228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2031778,0.0003549,0.7948648,0.0001740597,0.0001893715,0.0005318859,0.000004862878,0.0006811221,0.00002119685],"genre_scores_gemma":[0.8813885,0.000003555938,0.1179184,0.00001498828,0.0001309855,0.0001055138,0.00001799137,0.00003079635,0.0003892193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9118333,"threshold_uncertainty_score":0.6202589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07372243200853963,"score_gpt":0.3505859901875498,"score_spread":0.2768635581790102,"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."}}