{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005563901,0.00162855,0.001168373,0.005710367,0.001317609,0.002584539,0.002049134,0.001591783,0.003525876],"category_scores_gemma":[0.02151408,0.0006331345,0.001694673,0.002905337,0.0008726656,0.002440399,0.001202918,0.002245272,0.002719305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519989,"about_ca_system_score_gemma":0.002682698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009927927,"about_ca_topic_score_gemma":0.01209579,"domain_scores_codex":[0.9948757,0.001992767,0.0005772773,0.001254541,0.001082316,0.000217455],"domain_scores_gemma":[0.9893361,0.007538313,0.0006985217,0.0006412129,0.001611786,0.0001740457],"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":[0.0005701861,0.0005982768,0.02130796,0.0007807732,0.0002143324,0.0004475425,0.00079819,0.06390419,0.006978954,0.01079068,0.01990375,0.8737053],"study_design_scores_gemma":[0.0000780398,0.0001002271,0.002281972,0.000157528,0.00005914536,0.0002912531,0.0002768372,0.9546323,0.003935631,0.03080124,0.0073342,0.0000516098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03764554,0.0009264834,0.9475987,0.0009197662,0.0002487686,0.0006683058,0.001677228,0.007264142,0.003050977],"genre_scores_gemma":[0.1990462,0.0003730193,0.7908959,0.0005453856,0.0001991401,0.0009710726,0.00541907,0.0003404018,0.002209795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009927927,"threshold_uncertainty_score":0.02942508,"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."}}