{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009139612,0.001014339,0.001165211,0.00382516,0.001081624,0.001353669,0.001268197,0.001086074,0.002588132],"category_scores_gemma":[0.002722246,0.0003141297,0.0009903111,0.004413353,0.0006856423,0.002055679,0.0007406478,0.001215602,0.002657062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005715368,"about_ca_system_score_gemma":0.001418097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002836044,"about_ca_topic_score_gemma":0.004402585,"domain_scores_codex":[0.998144,0.0001941024,0.0001561106,0.0004855696,0.0009135985,0.0001066095],"domain_scores_gemma":[0.9986077,0.0003186032,0.0001517272,0.0002221374,0.0006509615,0.00004882686],"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":[0.0001097721,0.0001067582,0.001371612,0.0002118152,0.00006784996,0.0001030106,0.0001174155,0.004956872,0.02075726,0.004952312,0.01144511,0.9558003],"study_design_scores_gemma":[0.00007957684,0.000267539,0.00567527,0.00008426273,0.0001126734,0.001674,0.000243353,0.8578352,0.05215184,0.01610956,0.06564753,0.0001192755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005259476,0.0004788558,0.9897448,0.0001746318,0.0003277539,0.0002176302,0.0003651379,0.002073393,0.001358295],"genre_scores_gemma":[0.06754955,0.0006322385,0.9207641,0.0002007881,0.0003599625,0.0003968635,0.001325671,0.0001583315,0.008612383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00382516,"threshold_uncertainty_score":0.008658111,"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."}}