{"id":"W3183335868","doi":"10.1007/978-3-030-79457-6_48","title":"Collapsed Gibbs Sampling of Beta-Liouville Multinomial for Short Text Clustering","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Gibbs sampling; Multinomial distribution; Cluster analysis; Sampling (signal processing); Social media; Data mining; Artificial intelligence; World Wide Web; Statistics; Mathematics; Bayesian probability","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":[0.0081256,0.001130058,0.003012998,0.004110675,0.002443498,0.003685984,0.005766449,0.003623839,0.007979943],"category_scores_gemma":[0.03540904,0.001494093,0.002978465,0.005043009,0.002517549,0.00450423,0.004149835,0.003395226,0.002950497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002663674,"about_ca_system_score_gemma":0.002399196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.010175,"about_ca_topic_score_gemma":0.0174826,"domain_scores_codex":[0.9943091,0.003464892,0.0002711318,0.0009961582,0.0006086827,0.0003500972],"domain_scores_gemma":[0.9764355,0.01871457,0.0004538731,0.002219627,0.001498102,0.0006784213],"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":[0.0009092289,0.0003794128,0.004304995,0.0007000974,0.0004529217,0.0004500887,0.00159082,0.4200938,0.005907631,0.3314133,0.01938857,0.2144091],"study_design_scores_gemma":[0.00002418617,0.00001728607,0.0002428541,0.0000237559,0.00001603455,0.00003948071,0.00003941184,0.9310585,0.0003836031,0.06685813,0.001277102,0.00001961643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0128342,0.0005300724,0.984439,0.0002436928,0.0001002426,0.0001249843,0.0003731991,0.0006283327,0.0007263072],"genre_scores_gemma":[0.3287899,0.001174767,0.6390702,0.000709511,0.000870673,0.001718744,0.009291771,0.001623101,0.01675142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.010175,"threshold_uncertainty_score":0.0429728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04681323560420386,"score_gpt":0.2805330171014423,"score_spread":0.2337197814972384,"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."}}