{"id":"W2133556763","doi":"10.1007/3-540-47922-8_14","title":"Topic Discovery from Text Using Aggregation of Different Clustering Methods","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Measure (data warehouse); Clustering high-dimensional data; Data mining; Process (computing); Cluster (spacecraft); Vocabulary; Artificial intelligence; Correlation clustering; Machine learning; Information retrieval","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":[0.00481289,0.001561571,0.002267954,0.01445396,0.001806322,0.003806309,0.002000039,0.001599305,0.001919192],"category_scores_gemma":[0.01222852,0.0006508968,0.00283672,0.01372608,0.0004843724,0.00297484,0.002460296,0.001240277,0.002047814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007787769,"about_ca_system_score_gemma":0.001245735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004424952,"about_ca_topic_score_gemma":0.009474416,"domain_scores_codex":[0.9954222,0.001066203,0.0005107737,0.00127596,0.001342047,0.0003828142],"domain_scores_gemma":[0.9906304,0.004643661,0.0004298237,0.001319941,0.002638512,0.0003375453],"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":[0.001370631,0.000431924,0.01357545,0.0009103976,0.0009174359,0.0002167724,0.001485485,0.01021014,0.03961224,0.002226663,0.01240403,0.9166389],"study_design_scores_gemma":[0.0003345777,0.0006283208,0.04418621,0.0002422451,0.002665455,0.001026741,0.002242767,0.809357,0.07135933,0.03724932,0.03032778,0.0003802708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0917286,0.003619302,0.8905331,0.0004455349,0.0004352691,0.0006850226,0.003153329,0.006394601,0.003005181],"genre_scores_gemma":[0.2086412,0.001111351,0.7750306,0.00009836323,0.0005026375,0.0005082167,0.009695867,0.0006929068,0.003719025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01445396,"threshold_uncertainty_score":0.02545333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03332615904962769,"score_gpt":0.3142565827528983,"score_spread":0.2809304237032706,"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."}}