{"id":"W4256061005","doi":"10.32920/ryerson.14665455","title":"Speeding up calibration of latent Dirichlet allocation model to improve topic analysis in software engineering","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Exploit; Software; Simple (philosophy); Dirichlet distribution; Information retrieval; Data mining; Data science; Theoretical computer science; 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":[0.01143105,0.001254036,0.001596161,0.003162596,0.00144876,0.00314657,0.001902172,0.002173908,0.003168236],"category_scores_gemma":[0.06728162,0.001094646,0.001515389,0.002870911,0.001215874,0.006110901,0.004041422,0.004580087,0.00239453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001556373,"about_ca_system_score_gemma":0.002538848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00687847,"about_ca_topic_score_gemma":0.00745724,"domain_scores_codex":[0.9928925,0.004406427,0.0003664192,0.001262533,0.0007583147,0.0003137796],"domain_scores_gemma":[0.9717367,0.0223188,0.0008330427,0.002463382,0.00231137,0.000336771],"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":[0.0004774432,0.0003240684,0.01078921,0.0004557642,0.0002536701,0.0001944982,0.002638991,0.4177869,0.0111376,0.05880273,0.01017349,0.4869657],"study_design_scores_gemma":[0.000036799,0.00003084851,0.0009502133,0.00003598884,0.0000229574,0.00005086152,0.0001450951,0.9486023,0.002643851,0.04468168,0.002757736,0.00004171551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0160747,0.0004281268,0.9811916,0.0003521687,0.00007010012,0.00007861936,0.0001012734,0.001022081,0.0006814259],"genre_scores_gemma":[0.2628559,0.0006363863,0.7319005,0.000344349,0.0001991248,0.0006269001,0.001082696,0.0006688682,0.001685292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01143105,"threshold_uncertainty_score":0.06045389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02762228010359115,"score_gpt":0.2732267524094578,"score_spread":0.2456044723058666,"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."}}