{"id":"W2107131706","doi":"10.1109/icdm.2006.64","title":"Enhancing Text Clustering Using Concept-based Mining Model","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Phrase; Sentence; Document clustering; Term (time); Semantics (computer science); Similarity (geometry); Natural language processing; Matching (statistics); Artificial intelligence; Similarity measure; Measure (data warehouse); Word (group theory); Information retrieval; Data mining; Mathematics; Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002650612,0.0001665911,0.0001968173,0.0001791413,0.0002327842,0.0004143846,0.0006000313,0.00005770642,0.000008028982],"category_scores_gemma":[0.00003236112,0.000169082,0.00007546115,0.0005237807,0.00003686682,0.0008077928,0.0002177562,0.0001013175,0.00001301231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006421212,"about_ca_system_score_gemma":0.00007187897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001098797,"about_ca_topic_score_gemma":0.000009324203,"domain_scores_codex":[0.9985927,0.000004598875,0.0002820373,0.0004687291,0.0002708287,0.0003811437],"domain_scores_gemma":[0.9994678,0.00002434367,0.0001457513,0.0001745945,0.0001186041,0.00006887153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001776958,0.0002021106,0.0083932,0.000219493,0.00007602124,0.00002750245,0.0060079,0.3411702,0.5899568,0.01583744,0.004719516,0.03337212],"study_design_scores_gemma":[0.0001752626,0.00001215116,0.00005254959,0.00007384234,0.00001685673,0.000006994339,0.0001076815,0.9693813,0.02955339,0.0002060807,0.0001996042,0.0002142969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2178031,0.00003780846,0.7789806,0.0001478699,0.00005275437,0.00003924304,0.000001307372,0.0002242336,0.002713092],"genre_scores_gemma":[0.6854144,2.633038e-7,0.314116,0.0001518211,0.00009571074,0.000003445618,0.000003213546,0.00001134613,0.0002037554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6282111,"threshold_uncertainty_score":0.6894965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02220185227204753,"score_gpt":0.2452552487338726,"score_spread":0.223053396461825,"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."}}