{"id":"W4318606113","doi":"10.1109/ssci51031.2022.10022116","title":"Improving Topic Quality with Interactive Beta-Liouville Mixture Allocation Model","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Inference; Cluster analysis; Categorization; Artificial intelligence; Dirichlet distribution; Natural language processing; Task (project management); Machine learning; Set (abstract data type); Quality (philosophy); Hierarchical Dirichlet process; BETA (programming language); Mathematics","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":[0.00650733,0.001221409,0.002115044,0.001814728,0.001106233,0.002677516,0.003410499,0.002435758,0.002357789],"category_scores_gemma":[0.01709834,0.0009379507,0.001927339,0.001885043,0.001149956,0.005460645,0.002930112,0.003153789,0.002025031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001521844,"about_ca_system_score_gemma":0.001604595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006553198,"about_ca_topic_score_gemma":0.007148977,"domain_scores_codex":[0.9968641,0.001542795,0.0001828049,0.0006116936,0.000557757,0.0002408176],"domain_scores_gemma":[0.992708,0.004762343,0.00035094,0.0008623204,0.001028405,0.0002879789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001338398,0.0006674926,0.007860336,0.0002760802,0.0003657572,0.000226339,0.001432741,0.5077273,0.01544493,0.03320675,0.009338727,0.4221152],"study_design_scores_gemma":[0.00003220499,0.00002987903,0.0002386845,0.000006805872,0.00002140777,0.00003276194,0.00002757222,0.9898545,0.00142226,0.007397053,0.000919444,0.00001743861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01702174,0.0005123237,0.9796708,0.0002357965,0.00005202465,0.00006300148,0.00006614479,0.001440713,0.0009373673],"genre_scores_gemma":[0.5535619,0.0008683401,0.4371777,0.000581591,0.0002652334,0.0005101773,0.00110938,0.0009022602,0.00502337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006553198,"threshold_uncertainty_score":0.03441441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02637901145546341,"score_gpt":0.2805629512311266,"score_spread":0.2541839397756632,"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."}}