{"id":"W2001738847","doi":"10.5539/mas.v3n9p72","title":"A New Method of Hierarchical Text Clustering Based on Lsa-Hgsom","year":2009,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Brown clustering; Correlation clustering; Latent semantic analysis; Data mining; Single-linkage clustering; Artificial intelligence; Clustering high-dimensional data; CURE data clustering algorithm; Vector space model; Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009855616,0.001083714,0.001248921,0.004179923,0.001565368,0.001182966,0.001733876,0.001095095,0.002994527],"category_scores_gemma":[0.003055604,0.0004804168,0.002098073,0.004564978,0.0008940349,0.002067958,0.001487056,0.001170441,0.001755837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027676,"about_ca_system_score_gemma":0.002093883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008963278,"about_ca_topic_score_gemma":0.009268267,"domain_scores_codex":[0.9978562,0.0003581264,0.0001655988,0.0005975232,0.0008974283,0.0001251163],"domain_scores_gemma":[0.9990822,0.0001915403,0.00007927219,0.0001312357,0.0004681708,0.00004748122],"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":[0.0001636976,0.0001351257,0.001779977,0.0003204782,0.0002558678,0.0001577886,0.0005591178,0.05446017,0.01984672,0.01988437,0.01028635,0.8921503],"study_design_scores_gemma":[0.00007191009,0.0001022681,0.00178577,0.00003087992,0.000092961,0.0002697558,0.0002379141,0.9389012,0.01161133,0.03030157,0.01649732,0.00009720327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003486909,0.0001464551,0.993992,0.00009084088,0.00007745455,0.00008588495,0.0001366678,0.001123617,0.0008601199],"genre_scores_gemma":[0.05188891,0.0001750041,0.9430724,0.0001203372,0.00008749818,0.0003064712,0.0007565721,0.00022716,0.00336556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008963278,"threshold_uncertainty_score":0.01782221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02084772498625357,"score_gpt":0.3289332041387431,"score_spread":0.3080854791524895,"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."}}