{"id":"W4321793856","doi":"10.1016/j.jss.2023.111651","title":"Finding associations between natural and computer languages: A case-study of bilingual LDA applied to the bleeping computer forum posts","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Blackberry (Canada); Lakehead University; Queen's University","funders":"","keywords":"Perplexity; Computer science; Topic model; Natural language processing; Context (archaeology); Latent Dirichlet allocation; Artificial intelligence; Coherence (philosophical gambling strategy); Natural language; Software; Language model; Statistics; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.003751612,0.0002792059,0.0003922427,0.003245863,0.00323728,0.001554316,0.0005835404,0.0008714159,0.002392235],"category_scores_gemma":[0.02051327,0.000198197,0.0002445469,0.003572997,0.001204114,0.002173088,0.001802386,0.000883284,0.0005855195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008790951,"about_ca_system_score_gemma":0.001798457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01780938,"about_ca_topic_score_gemma":0.04309026,"domain_scores_codex":[0.9967455,0.002116522,0.0001464777,0.0003513901,0.0003834323,0.0002566193],"domain_scores_gemma":[0.9759341,0.01949549,0.001003517,0.0009818849,0.001874345,0.0007104961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001849371,0.001804384,0.6115392,0.0008976154,0.0001250927,0.005517858,0.1604172,0.0007783431,0.02462023,0.005162297,0.004004218,0.1832843],"study_design_scores_gemma":[0.0001750695,0.001101562,0.5811534,0.0004056057,0.0003724242,0.01038239,0.2934663,0.03051521,0.02465362,0.01039043,0.04716163,0.0002224317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914596,0.0001533763,0.004649297,0.0002340208,0.00001222381,0.00006819245,0.0002464007,0.00005520113,0.003121629],"genre_scores_gemma":[0.9938942,0.00008414612,0.004318078,0.00005425437,0.000009782821,0.00004184647,0.0002982687,0.00003611081,0.00126322],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01780938,"threshold_uncertainty_score":0.03541148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02679858553327135,"score_gpt":0.2989785756976393,"score_spread":0.2721799901643679,"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."}}