{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002289909,0.0001617689,0.0001777257,0.0001522551,0.0005358078,0.0002844022,0.0004227238,0.00008439587,5.975227e-7],"category_scores_gemma":[0.00001161284,0.0001441442,0.00003404803,0.0007113921,0.00004560266,0.0003178364,0.00009379636,0.00006532325,0.00002658283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007500708,"about_ca_system_score_gemma":0.0001066389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001521896,"about_ca_topic_score_gemma":0.00002429199,"domain_scores_codex":[0.9985534,0.00002430314,0.0003369277,0.0006045816,0.0002147673,0.0002660008],"domain_scores_gemma":[0.9986436,0.00009351487,0.0001360645,0.000760556,0.0002547648,0.0001115442],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001061813,0.00005792942,0.0008274826,0.00007380421,0.00003138094,1.873979e-7,0.0009871664,0.3003218,0.001450114,0.6907744,0.001437747,0.004027362],"study_design_scores_gemma":[0.0004489275,0.00001973683,0.0003919603,0.00001387533,0.000005409255,0.000006059167,0.00003628727,0.9808083,0.00006801573,0.004339801,0.01367202,0.0001896258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001650715,0.0003266612,0.9935642,0.0007486469,0.00005643523,0.002834542,0.00001088201,0.0005845994,0.0002233485],"genre_scores_gemma":[0.6839738,0.0002181923,0.2455681,0.0002029741,0.0002825256,0.06682387,0.0001099021,0.00003763329,0.00278299],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.747996,"threshold_uncertainty_score":0.5878029,"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."}}