{"id":"W4412512470","doi":"10.1007/978-981-96-6688-1_28","title":"A Simultaneous Hierarchical Count Data Clustering and Feature Selection Based on Multinomial Nested Dirichlet Mixture Using the Minorization-Maximization Framework","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Multinomial distribution; Feature selection; Latent Dirichlet allocation; Selection (genetic algorithm); Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Maximization; Hierarchical clustering; Count data; Data mining; Artificial intelligence; Statistics; Topic model; Mathematics; Mathematical optimization","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006655192,0.0002485391,0.0002104418,0.0008408862,0.0009953588,0.001168607,0.003597322,0.0002826685,0.000002242249],"category_scores_gemma":[0.0004493285,0.0002060738,0.00002337503,0.0008814079,0.0006822341,0.003012579,0.002694441,0.0007538609,0.000002437984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001722504,"about_ca_system_score_gemma":0.0003477711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009885718,"about_ca_topic_score_gemma":0.0000156035,"domain_scores_codex":[0.9983697,0.00006312006,0.0004797798,0.0004527055,0.0004361421,0.0001985615],"domain_scores_gemma":[0.995524,0.001103335,0.0003654629,0.002618829,0.0003348286,0.00005353286],"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":[0.00002207639,0.00004633843,0.0002572862,0.00008161707,0.00001388448,6.972933e-7,0.00137709,0.04714974,0.00001221598,0.4857438,0.0006323277,0.4646629],"study_design_scores_gemma":[0.000185129,0.00003166114,0.0002831016,0.0002461017,0.000009719346,0.000008951532,0.00001836851,0.9649313,0.000004723033,0.002110883,0.03196694,0.0002031268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000365189,0.0001530619,0.9903281,0.004952701,0.0002508422,0.0005408319,0.00002835289,0.0001791069,0.003530476],"genre_scores_gemma":[0.1753698,0.001220245,0.8190333,0.003120481,0.00008878454,0.00003881802,0.0003842513,0.00001658915,0.0007278294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9177815,"threshold_uncertainty_score":0.9998683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0348103726767342,"score_gpt":0.3026684632058938,"score_spread":0.2678580905291596,"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."}}