{"id":"W4239379014","doi":"10.4018/9781591405573.ch105","title":"Hierarchical Document Clustering","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Document clustering; Cluster analysis; Hierarchy; Hierarchical clustering; Computer science; Directory; Information retrieval; Tree (set theory); Subject (documents); Similarity (geometry); Complete-linkage clustering; 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":[0.002237274,0.001609564,0.00169051,0.01197213,0.001982312,0.004818681,0.00295081,0.001335526,0.02312193],"category_scores_gemma":[0.008381198,0.0005918996,0.001865124,0.01614024,0.0007094205,0.003119934,0.002062702,0.001404138,0.03212331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001829755,"about_ca_system_score_gemma":0.003579597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007145505,"about_ca_topic_score_gemma":0.01102855,"domain_scores_codex":[0.9960134,0.0007866863,0.0003201689,0.001102444,0.001564684,0.0002125882],"domain_scores_gemma":[0.9961585,0.001049774,0.0002390881,0.00077864,0.00163105,0.0001429924],"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":[0.0001113288,0.0001130656,0.001533844,0.001565425,0.0002432486,0.00017956,0.0005347059,0.007150718,0.004508488,0.02289259,0.1568266,0.8043404],"study_design_scores_gemma":[0.0000763074,0.0001358078,0.004798617,0.0007735356,0.0003504147,0.001278638,0.0008159422,0.1208407,0.01369531,0.08762411,0.7694215,0.0001891813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006450752,0.01234535,0.8938096,0.001069183,0.0006660655,0.001700221,0.0225981,0.01559064,0.04577007],"genre_scores_gemma":[0.04505429,0.006133341,0.8722796,0.0003970236,0.0003665366,0.0007164252,0.03803143,0.001457029,0.03556426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02312193,"threshold_uncertainty_score":0.07735056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02025228869145076,"score_gpt":0.2686396202014081,"score_spread":0.2483873315099574,"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."}}