{"id":"W4237492828","doi":"10.4018/978-1-60566-010-3.ch150","title":"Hierarchical Document Clustering","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Concordia University","funders":"","keywords":"Hierarchical clustering; Cluster analysis; Document clustering; Brown clustering; Hierarchy; Computer science; Complete-linkage clustering; Directory; Hierarchical clustering of networks; Single-linkage clustering; Fuzzy clustering; Tree (set theory); Consensus clustering; Data mining; Information retrieval; Artificial intelligence; Canopy clustering algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001721455,0.001504093,0.001576036,0.009631068,0.001797087,0.005191956,0.002959881,0.001400224,0.02500525],"category_scores_gemma":[0.006422894,0.0005676554,0.00162915,0.01532099,0.0006551445,0.00344668,0.0021593,0.001336733,0.03146466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798029,"about_ca_system_score_gemma":0.002909532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005886948,"about_ca_topic_score_gemma":0.008169254,"domain_scores_codex":[0.9969702,0.0005828094,0.0002496144,0.0007779267,0.001257006,0.0001624737],"domain_scores_gemma":[0.9970304,0.0007848987,0.0001705188,0.0006054178,0.00130314,0.0001056006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007159584,0.0000663258,0.0009388465,0.001509938,0.0001701201,0.0001699089,0.0004286657,0.006984547,0.002688252,0.03187753,0.1681255,0.7869688],"study_design_scores_gemma":[0.00004182792,0.00007457755,0.002062451,0.0005590331,0.0001743527,0.001056089,0.0004992896,0.06439306,0.006746561,0.07926447,0.8450053,0.0001228246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004513395,0.02000075,0.8727955,0.001306456,0.0009435295,0.001511588,0.01741595,0.01156039,0.0699525],"genre_scores_gemma":[0.03840612,0.01239637,0.8595881,0.000606933,0.0005556539,0.0008078556,0.03370426,0.00123184,0.05270287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02500525,"threshold_uncertainty_score":0.08365089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01764110702382957,"score_gpt":0.2608393151589307,"score_spread":0.2431982081351011,"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."}}