{"id":"W2099126842","doi":"10.1109/icdm.2001.989592","title":"A simple KNN algorithm for text categorization","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Text categorization; Feature (linguistics); Context (archaeology); Vocabulary; Feature selection; Word (group theory); Categorization; Simple (philosophy); Class (philosophy); k-nearest neighbors algorithm; Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology); 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":[0.002183947,0.002020608,0.001527363,0.004818519,0.001920708,0.002100165,0.002703072,0.002684817,0.009330341],"category_scores_gemma":[0.007986929,0.0005954772,0.00146442,0.005167935,0.001001479,0.003672694,0.001564922,0.002167924,0.01295996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001123079,"about_ca_system_score_gemma":0.002013379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004765752,"about_ca_topic_score_gemma":0.006579669,"domain_scores_codex":[0.9964685,0.0005496865,0.0003592005,0.0009805036,0.001472677,0.0001694898],"domain_scores_gemma":[0.9981555,0.000533679,0.0001543539,0.0003339213,0.0007570608,0.00006551814],"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":[0.0001094679,0.0001143501,0.0006807648,0.000405163,0.0001243681,0.00008221358,0.0001017859,0.02014195,0.006105151,0.01052688,0.02219839,0.9394094],"study_design_scores_gemma":[0.0001593808,0.0003217575,0.002698133,0.0003399825,0.0001823433,0.001369898,0.0002358906,0.6179875,0.02085824,0.1748949,0.1806987,0.0002533497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002073414,0.001005024,0.9890928,0.0002647378,0.0003586765,0.0004822347,0.0006074676,0.002709447,0.003406155],"genre_scores_gemma":[0.02206756,0.0007411701,0.9652344,0.0003310904,0.0002161739,0.0005842369,0.001518199,0.0002148558,0.009092454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009330341,"threshold_uncertainty_score":0.03121305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03016497877693925,"score_gpt":0.2537802900861292,"score_spread":0.22361531130919,"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."}}