{"id":"W4367319399","doi":"10.1016/j.eswa.2023.120262","title":"A context-enhanced Dirichlet model for online clustering in short text streams","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Cluster analysis; Latent Dirichlet allocation; Inference; Data mining; Artificial intelligence; Topic model; Exploit; Machine learning","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":[0.0002821407,0.0001623771,0.0002747151,0.0001373415,0.0001367038,0.0001286012,0.0005719742,0.00007810845,5.58214e-7],"category_scores_gemma":[0.00001000743,0.0001429606,0.00004805011,0.000719925,0.00002655063,0.0001996556,0.0001044495,0.00009261362,0.000009746124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000626968,"about_ca_system_score_gemma":0.00007743033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002065597,"about_ca_topic_score_gemma":0.0008009969,"domain_scores_codex":[0.9985672,0.00003989701,0.0003361586,0.0005422138,0.0001727789,0.0003416985],"domain_scores_gemma":[0.9988883,0.0001288534,0.00005031933,0.0007326347,0.00009396065,0.0001059434],"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":[0.00005025585,0.0005273797,0.0001320004,0.0002690683,0.00009208426,0.000008572695,0.01158726,0.07083287,0.01477181,0.1274062,0.009378562,0.7649439],"study_design_scores_gemma":[0.0003214798,0.00002969798,0.00004208121,0.00007079288,0.000002581314,0.000005906537,0.0001813962,0.9925421,0.0001796785,0.001107864,0.005318941,0.0001974247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00113806,0.0002817608,0.995576,0.0004833892,0.00007494458,0.001765384,0.00003533459,0.0003285561,0.0003166262],"genre_scores_gemma":[0.6257473,0.0000295958,0.3657905,0.0001932907,0.0001199703,0.007028979,0.0000381275,0.00002731877,0.001024943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9217093,"threshold_uncertainty_score":0.5829763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04279014910143022,"score_gpt":0.3247153135910042,"score_spread":0.2819251644895739,"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."}}