{"id":"W4387107464","doi":"10.1016/j.eswa.2023.121720","title":"Parallel inference for cross-collection latent generalized Dirichlet allocation model and applications","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Inference; Topic model; Hierarchical Dirichlet process; Prior probability; Dirichlet distribution; Scalability; Machine learning; Data mining; Artificial intelligence; Mathematics; Bayesian probability; Database","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":[0.009639892,0.001656268,0.003738731,0.002300333,0.001990577,0.003059335,0.005248616,0.002193905,0.008430622],"category_scores_gemma":[0.02639019,0.002202703,0.003298755,0.004060421,0.001580534,0.005539989,0.004380067,0.004794232,0.003099947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002305605,"about_ca_system_score_gemma":0.004344349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02246284,"about_ca_topic_score_gemma":0.03794692,"domain_scores_codex":[0.9941817,0.002994392,0.0003255598,0.00149286,0.0006593911,0.0003460401],"domain_scores_gemma":[0.987872,0.007729893,0.0003204229,0.002574112,0.001189418,0.0003141286],"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":[0.001029644,0.0005692597,0.003529765,0.000488135,0.0008090765,0.000273637,0.000589207,0.4002445,0.003525986,0.106898,0.01833593,0.4637069],"study_design_scores_gemma":[0.00005903591,0.00001879093,0.0002902833,0.00001248621,0.00005660966,0.00003518263,0.00003113277,0.9268906,0.0006144387,0.07042543,0.001546248,0.00001991194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005634527,0.0004587632,0.9912921,0.0003229021,0.0001111873,0.00006509414,0.0003110803,0.001203545,0.0006008789],"genre_scores_gemma":[0.1994502,0.000926637,0.784548,0.0005473286,0.0006337913,0.0007696313,0.004025059,0.001092028,0.008007443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02246284,"threshold_uncertainty_score":0.05098122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04492236747625851,"score_gpt":0.3183281375651033,"score_spread":0.2734057700888448,"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."}}