{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001402207,0.0005055546,0.0005475691,0.0001310922,0.000103091,0.0001600207,0.001866711,0.0003660624,0.00004765934],"category_scores_gemma":[0.000009006889,0.0004927001,0.0003515467,0.00002972616,0.0001231037,0.000171652,0.001519887,0.0004435456,0.0002956077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003582812,"about_ca_system_score_gemma":0.0001147371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003770234,"about_ca_topic_score_gemma":0.00006748919,"domain_scores_codex":[0.9976413,0.00002215611,0.0004920561,0.0008749492,0.0005240881,0.0004454238],"domain_scores_gemma":[0.9979175,0.00002605462,0.0002713767,0.001465852,0.00009358286,0.0002256494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005155928,0.00000436249,0.000001259418,0.00000981099,0.00006201008,0.00009691632,0.00003808004,0.00000184203,0.000008279593,0.9299468,0.000541814,0.06928363],"study_design_scores_gemma":[0.00009926884,0.00007983897,0.000004576972,0.0001109484,0.00003589917,0.00005211142,3.612231e-7,0.0001616644,0.0001459262,0.9378744,0.06095165,0.0004832983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.000001264316,0.0001061171,0.4173635,0.00003693134,0.000142341,0.000151699,0.000004651903,0.0005363108,0.5816572],"genre_scores_gemma":[0.08476903,0.00004743769,0.4998452,0.002107991,0.0006397279,0.00009365625,0.000005778049,0.0001514771,0.4123397],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1693175,"threshold_uncertainty_score":0.9997525,"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."}}