{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003254672,0.001569087,0.004011118,0.002037213,0.001736908,0.002235496,0.00620163,0.001677013,0.003468547],"category_scores_gemma":[0.007908129,0.001511095,0.003620744,0.003593362,0.001442439,0.003009317,0.00497997,0.002544629,0.002488606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001434762,"about_ca_system_score_gemma":0.002266384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008089202,"about_ca_topic_score_gemma":0.01279458,"domain_scores_codex":[0.9965647,0.001242374,0.0002013279,0.0008346193,0.0008971014,0.0002599192],"domain_scores_gemma":[0.9965223,0.001897307,0.0001662396,0.0005129294,0.0007379794,0.0001632755],"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":[0.0006092833,0.0003431709,0.002046232,0.0004148493,0.0005228596,0.0002988333,0.0007351476,0.1901113,0.02400553,0.07533959,0.0159178,0.6896554],"study_design_scores_gemma":[0.00001633296,0.00003127278,0.0002982566,0.000008831851,0.00003191797,0.00008904972,0.00003448089,0.9747898,0.002152965,0.02057426,0.001939425,0.00003350494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00130901,0.00006543446,0.9979831,0.00003565674,0.00001537777,0.00002776738,0.00004120686,0.0003536065,0.0001688576],"genre_scores_gemma":[0.03465008,0.0001334773,0.9608267,0.00009681075,0.00009128086,0.0002859987,0.0007155222,0.0003790677,0.002821061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008089202,"threshold_uncertainty_score":0.01721251,"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."}}