{"id":"W2029219570","doi":"10.1145/2644866.2644868","title":"An ensemble approach for text document clustering using Wikipedia concepts","year":2014,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidade Federal de Minas Gerais","keywords":"Document clustering; Computer science; Cluster analysis; Term (time); Information retrieval; Representation (politics); tf–idf; Text corpus; Artificial intelligence; Feature (linguistics); Natural language processing; Document retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004472386,0.0001045429,0.0001528485,0.00006587416,0.0001426124,0.0003006323,0.000616674,0.00003579054,0.000009260011],"category_scores_gemma":[0.00002183538,0.0000885186,0.00005736041,0.0001590042,0.00002069413,0.0006010528,0.0001515623,0.00004040293,0.000008459495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002076271,"about_ca_system_score_gemma":0.00002226384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008970182,"about_ca_topic_score_gemma":0.0000103453,"domain_scores_codex":[0.9989926,0.0000496591,0.0001620677,0.0003998142,0.0001443467,0.0002515388],"domain_scores_gemma":[0.9991404,0.0000583204,0.00005627042,0.0006012323,0.00004127295,0.0001025467],"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":[0.00002220846,0.0003506509,0.001487829,0.0001486824,0.0001614405,0.000003221289,0.004312338,0.0892178,0.0388588,0.1212252,0.004264876,0.739947],"study_design_scores_gemma":[0.0002123238,0.00006230462,0.0000319341,0.000004870831,0.00001306785,0.000003816182,0.00009954444,0.9955357,0.001466105,0.000296376,0.002129764,0.0001442377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01376059,0.000009828727,0.9822643,0.00006234758,0.00008876205,0.00007689876,0.000001258244,0.0001150246,0.00362101],"genre_scores_gemma":[0.5258442,5.50834e-7,0.4736483,0.0001666635,0.00009505772,0.000005870849,0.000008639014,0.000004603715,0.0002261654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9063178,"threshold_uncertainty_score":0.3609684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03155555860397413,"score_gpt":0.3061687329010991,"score_spread":0.274613174297125,"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."}}