{"id":"W2347899776","doi":"","title":"Short Text Categorization","year":2007,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Categorization; Automatism (medicine); Naive Bayes classifier; Recall; Basis (linear algebra); Artificial intelligence; Process (computing); Bayes' theorem; k-nearest neighbors algorithm; Pattern recognition (psychology); Machine learning; Cognitive psychology; Mathematics; Bayesian probability; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00139859,0.001005908,0.0006674554,0.007665208,0.001207069,0.002162677,0.0009135616,0.0007345697,0.02451575],"category_scores_gemma":[0.007149502,0.0001364798,0.0006702173,0.006819348,0.0004872225,0.003430998,0.0009480806,0.0005603774,0.01178562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006434813,"about_ca_system_score_gemma":0.0007878341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001146132,"about_ca_topic_score_gemma":0.001401167,"domain_scores_codex":[0.9981843,0.0003724167,0.0002885651,0.0003858748,0.0006903647,0.00007843703],"domain_scores_gemma":[0.9950697,0.001831691,0.0005472116,0.0006521996,0.001709222,0.0001899025],"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":[0.0003523272,0.0001368525,0.004757468,0.001378192,0.0001134303,0.0003256669,0.0005846712,0.0009991991,0.01533868,0.02490107,0.04357201,0.9075404],"study_design_scores_gemma":[0.0001087883,0.001336415,0.04150255,0.0007258828,0.0002618691,0.003951188,0.002802607,0.0478374,0.03131292,0.1565911,0.7133154,0.0002538774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0878926,0.02345641,0.7148575,0.003247036,0.007330748,0.003237917,0.02341047,0.007834934,0.1287323],"genre_scores_gemma":[0.3108078,0.006454581,0.5400118,0.00163885,0.003130689,0.001674544,0.04685695,0.0007535936,0.08867131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02451575,"threshold_uncertainty_score":0.08201337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009766544396552829,"score_gpt":0.2810593079254856,"score_spread":0.2712927635289327,"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."}}