{"id":"W78181647","doi":"10.4018/978-1-59140-557-3.ch105","title":"Hierarchical Document Clustering","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Document clustering; Hierarchy; Hierarchical clustering; Directory; Computer science; Tree (set theory); Complete-linkage clustering; Information retrieval; Subject (documents); Similarity (geometry); Cluster (spacecraft); Fuzzy clustering; Artificial intelligence; World Wide Web; Canopy clustering algorithm; Mathematics; Combinatorics","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":[0.001483542,0.001270724,0.001310813,0.008322293,0.001464979,0.004061158,0.002734652,0.001156277,0.03069563],"category_scores_gemma":[0.004875119,0.0005605534,0.001435262,0.01253986,0.0005367883,0.002838817,0.001924796,0.001215231,0.03842956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514951,"about_ca_system_score_gemma":0.002312419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004318473,"about_ca_topic_score_gemma":0.007087165,"domain_scores_codex":[0.9979127,0.0003776257,0.0001491424,0.0005235279,0.0009322361,0.0001046913],"domain_scores_gemma":[0.9976385,0.0006591607,0.000122143,0.0005232258,0.0009549023,0.0001021598],"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":[0.00004937048,0.00006195813,0.0006438035,0.001130077,0.0001395762,0.0001198863,0.0003546409,0.005750896,0.002722592,0.0274153,0.1843121,0.7772997],"study_design_scores_gemma":[0.00003466036,0.0000583583,0.001823168,0.0004655656,0.0001439785,0.0009194686,0.0003332206,0.05067008,0.006170684,0.06923957,0.8700439,0.00009728688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004242405,0.02182215,0.8560191,0.001390907,0.000869569,0.001026055,0.01256401,0.01218408,0.08988167],"genre_scores_gemma":[0.03385403,0.01180082,0.8535339,0.0005766616,0.0004937847,0.0005191383,0.0254075,0.00159493,0.07221925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03069563,"threshold_uncertainty_score":0.1026871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01801288396838465,"score_gpt":0.2617875641419577,"score_spread":0.243774680173573,"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."}}