{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005836937,0.0003231957,0.0003038223,0.000250732,0.0007677199,0.0002529648,0.001314471,0.00006268042,0.00009101137],"category_scores_gemma":[0.00002847266,0.0003206407,0.0001158951,0.000673626,0.00009173178,0.001079471,0.0004871258,0.0006132545,0.00002744251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004491108,"about_ca_system_score_gemma":0.0003772722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001733375,"about_ca_topic_score_gemma":0.00006203634,"domain_scores_codex":[0.99659,0.0002690106,0.0005914437,0.0009894673,0.001158143,0.0004020038],"domain_scores_gemma":[0.9982132,0.0002927279,0.0003596842,0.0006869445,0.0003202867,0.0001271861],"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":[0.00009139516,0.0001151243,0.00005132388,0.00002183088,0.00003588201,0.000009839929,0.002463926,0.8542347,0.0009893189,0.1363241,0.0001209209,0.005541591],"study_design_scores_gemma":[0.000140559,0.0004463639,0.00007604122,0.00001718884,0.00001071601,0.00004767128,0.0007909473,0.9742601,0.00452838,0.01899457,0.0002843348,0.0004031396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03179743,0.00004070713,0.9606055,0.004709563,0.001012384,0.000400223,0.00003307702,0.0002247933,0.00117631],"genre_scores_gemma":[0.9306989,0.000008000632,0.06644087,0.001348666,0.0001161724,0.0001969213,0.00005382916,0.00002696351,0.001109723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8989014,"threshold_uncertainty_score":0.9999245,"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."}}