{"id":"W2131912994","doi":"10.1109/icdew.2007.4401066","title":"Document Representation and Dimension Reduction for Text Clustering","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Document clustering; Artificial intelligence; Pattern recognition (psychology); Representation (politics); Context (archaeology); Benchmark (surveying); Word (group theory); Dimension (graph theory); Natural language processing; 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":[0.0002519525,0.00005118533,0.00004886976,0.00009647326,0.00009538406,0.00009624547,0.0001276294,0.0000355154,0.000004375647],"category_scores_gemma":[0.00002651994,0.00004410408,0.00001660649,0.0001410746,0.00002276869,0.0004909618,0.0001091903,0.00002629172,0.000005947546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002766852,"about_ca_system_score_gemma":0.000004532207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000107598,"about_ca_topic_score_gemma":0.000004462546,"domain_scores_codex":[0.999424,0.000005443623,0.0001390108,0.0002271151,0.00008821722,0.0001161542],"domain_scores_gemma":[0.9996092,0.00004577156,0.00005218328,0.0002315743,0.00003605157,0.00002517798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001482485,0.00001657826,0.0002019335,0.000008723651,0.000005199556,5.376764e-7,0.0003344176,0.00001773625,0.04210392,0.2377426,0.001683357,0.7178702],"study_design_scores_gemma":[0.001466735,0.0003680457,0.02085935,0.00002855552,0.00001283034,0.00007821995,0.002283142,0.0428228,0.7828527,0.1269625,0.02177699,0.0004881259],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03816921,0.00004274033,0.9575168,0.002445099,0.0002432149,0.0002159633,7.239156e-8,0.0003627986,0.001004096],"genre_scores_gemma":[0.8472134,0.00002110011,0.1516455,0.00004352581,0.00002076745,0.00001560046,0.000001408148,0.00000251112,0.001036171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8090442,"threshold_uncertainty_score":0.1798512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02785592813353458,"score_gpt":0.3078267137122061,"score_spread":0.2799707855786715,"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."}}