{"id":"W2590184703","doi":"10.29173/cais539","title":"A Text Categorization Model Based on Hidden Markov Models","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Categorization; Computer science; Artificial intelligence; Speech recognition; Scheme (mathematics); Natural language processing; Pattern recognition (psychology); Markov model; Markov chain; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000286643,0.0002388752,0.0003029132,0.0002532325,0.0001199579,0.002566639,0.00313775,0.0001665326,0.00001762498],"category_scores_gemma":[0.002954537,0.0001791287,0.0001189352,0.0005668741,0.0002378537,0.01320297,0.0005661661,0.0002094524,0.00001022382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006131256,"about_ca_system_score_gemma":0.0002229669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008382261,"about_ca_topic_score_gemma":0.000001477695,"domain_scores_codex":[0.9983023,0.00001485166,0.000426757,0.0003968566,0.0005260139,0.0003331549],"domain_scores_gemma":[0.9799871,0.00008776541,0.0006024148,0.0004180458,0.01882122,0.00008347502],"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":[0.00006869939,0.0004018703,0.01149907,0.0002443023,0.00005596024,3.954353e-7,0.01228268,0.001374408,0.03085908,0.8229778,0.01403952,0.1061962],"study_design_scores_gemma":[0.0003619605,0.000169153,0.006092852,0.00009678108,0.0000163093,0.000002234497,0.0004429281,0.8303863,0.03647765,0.124929,0.0007649063,0.0002598957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8053731,0.00006289099,0.1312139,0.02241327,0.0001955451,0.001238714,0.00005380396,0.0005949123,0.0388539],"genre_scores_gemma":[0.9864096,0.00002571897,0.01238699,0.0003172596,0.00001710534,0.00009695061,0.000002557689,0.00001472998,0.0007290773],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8290119,"threshold_uncertainty_score":0.9984688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02412627837014809,"score_gpt":0.2320305390974688,"score_spread":0.2079042607273207,"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."}}