{"id":"W2129546202","doi":"10.1109/tkde.2009.174","title":"An Efficient Concept-Based Mining Model for Enhancing Text Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sentence; Natural language processing; Phrase; Term (time); Similarity (geometry); Semantics (computer science); Cluster analysis; Artificial intelligence; Document clustering; Meaning (existential); Word (group theory); Measure (data warehouse); Information retrieval; Similarity measure; Semantic similarity; Data mining; Linguistics","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":[0.000262825,0.0001803386,0.0001905087,0.0002198206,0.0002098036,0.0001705563,0.0007010057,0.00005614471,0.000001667858],"category_scores_gemma":[0.000006700024,0.0001856918,0.00004853342,0.0002611228,0.00001251327,0.0005065864,0.000007252913,0.0001152264,0.00000330278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276966,"about_ca_system_score_gemma":0.00005162087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000271801,"about_ca_topic_score_gemma":0.00002273831,"domain_scores_codex":[0.9988211,0.00001339826,0.0002198609,0.0005637287,0.0001004537,0.0002814317],"domain_scores_gemma":[0.9987236,0.0001122982,0.00003214907,0.0009533399,0.00003945975,0.0001391547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004530902,0.00008491378,1.779571e-7,0.00001585297,0.00001214752,9.798123e-7,0.0005523343,0.9268813,0.003856711,0.00005512716,0.00005228357,0.06848367],"study_design_scores_gemma":[0.0003545949,0.0001017748,0.000004968153,0.00007302899,0.00003392881,0.000002615989,0.00003324074,0.9921582,0.006827439,0.00000272018,0.0001835741,0.0002238726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003891453,0.000129599,0.9952431,0.0000561388,0.0001894916,0.00009320914,0.000130284,0.0002380028,0.00002869334],"genre_scores_gemma":[0.8403625,0.000004060427,0.1594156,0.00006946542,0.00004538479,0.000009794446,0.00004544479,0.00001179664,0.0000359766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8364711,"threshold_uncertainty_score":0.7572293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02779020595604768,"score_gpt":0.2810140212831417,"score_spread":0.253223815327094,"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."}}