{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001035886,0.000315299,0.0002765759,0.00004882508,0.0001327857,0.0003236939,0.001396788,0.0002067892,0.00002996913],"category_scores_gemma":[0.00000406514,0.0003127058,0.0001368584,0.00001984991,0.00006912297,0.0001100221,0.0009790428,0.0002975149,0.0006052642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000201563,"about_ca_system_score_gemma":0.0001348924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002578129,"about_ca_topic_score_gemma":0.0000348905,"domain_scores_codex":[0.9982767,0.00000836758,0.0003336389,0.0006689535,0.0003825778,0.0003298234],"domain_scores_gemma":[0.9985074,0.00002506696,0.000130902,0.001088285,0.00004427566,0.0002040165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[9.511651e-7,0.000003770995,1.758664e-7,0.000004426463,0.00001753166,0.00001517265,0.00002022867,0.000004735522,0.000001340997,0.7413226,0.002459698,0.2561494],"study_design_scores_gemma":[0.0001668891,0.00004581235,0.000008920136,0.00009843672,0.00001758009,0.00008580929,9.484691e-7,0.004324547,0.000008266939,0.3908069,0.6040232,0.0004126753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.000002244769,0.000110431,0.1753081,0.0004403464,0.0002512806,0.0001730316,0.00007875486,0.0002468693,0.8233889],"genre_scores_gemma":[0.005482984,0.00002435199,0.5033494,0.002575538,0.00177405,0.00009974773,0.0000280758,0.00007599608,0.4865899],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6015635,"threshold_uncertainty_score":0.9999325,"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."}}