{"id":"W4365518837","doi":"10.54254/2755-2721/2/20220540","title":"A Novel Method for Text Classification Dealing with Local Data Structures and High Data Dimensionality","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Curse of dimensionality; Pattern recognition (psychology); Artificial intelligence; k-nearest neighbors algorithm; Feature vector; Correlation; Text categorization; Data mining; Data set; Set (abstract data type); Support vector machine; 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":[0.0002602247,0.0001065097,0.0001084363,0.00009455433,0.0001163642,0.0001155225,0.000554749,0.00004172914,6.827347e-7],"category_scores_gemma":[0.00002475916,0.00009262518,0.000005252235,0.0002261962,0.0000386847,0.000284417,0.0006077415,0.00006752712,0.00000113186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008983395,"about_ca_system_score_gemma":0.00002572834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009177982,"about_ca_topic_score_gemma":0.000001321101,"domain_scores_codex":[0.9990537,0.000003530682,0.0001441333,0.0005067694,0.0001642752,0.0001276533],"domain_scores_gemma":[0.9989734,0.0003802542,0.00005358051,0.0005185861,0.00003476261,0.00003947509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005397555,0.000005546889,0.0000131298,0.00002321439,0.00001967192,2.480068e-7,0.00002639773,0.06505388,0.001774969,0.8392015,0.00008826833,0.09378783],"study_design_scores_gemma":[0.0003143131,0.00001047661,0.01469895,0.000006893061,0.000008090632,0.000009907784,0.00005037416,0.9546636,0.00009890628,0.02903629,0.0009813552,0.0001208599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002741907,0.00004743331,0.9954544,0.001088292,0.0000347049,0.0001639818,0.00006828627,0.0003893635,0.00001164734],"genre_scores_gemma":[0.5098823,0.000005193674,0.4896564,0.00003428429,0.00001345872,0.00001528695,0.000384782,0.000005501825,0.000002695301],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8896097,"threshold_uncertainty_score":0.3777145,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0606275537143638,"score_gpt":0.2986352954388763,"score_spread":0.2380077417245126,"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."}}