{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000425371,0.0004848681,0.0007657057,0.0008399027,0.0001339624,0.0003431887,0.002553733,0.0002630654,0.00002027548],"category_scores_gemma":[0.00008666443,0.0004264961,0.0002129465,0.0005386478,0.0004238732,0.001137043,0.001750005,0.0005233883,0.00000265677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004086169,"about_ca_system_score_gemma":0.00009531182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006712999,"about_ca_topic_score_gemma":0.00005908306,"domain_scores_codex":[0.9967445,0.00007854369,0.0007005264,0.00129303,0.0007660639,0.0004173176],"domain_scores_gemma":[0.9969846,0.0006060808,0.0006005712,0.001565217,0.0001574328,0.00008611187],"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":[0.000001896643,0.00002263896,0.0000892818,0.00002404621,0.00001954649,0.00001360609,0.0003615721,0.02089625,0.003769016,0.004214272,8.506684e-7,0.970587],"study_design_scores_gemma":[0.00009476092,0.00005330077,0.0001073589,0.0004748441,0.00001856324,0.000008121784,9.316832e-8,0.7711266,0.03163757,0.1960215,0.00006284028,0.000394461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005633726,0.0005088438,0.9972793,0.0000828995,0.0006515499,0.0002405937,0.000003655969,0.0001339775,0.000535836],"genre_scores_gemma":[0.1144983,0.00007050322,0.8848969,0.0001576784,0.0001949037,0.000003591282,0.000003152783,0.00002438669,0.0001505965],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9701926,"threshold_uncertainty_score":0.9998187,"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."}}