{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00135378,0.0006075334,0.0009379829,0.002159924,0.000663975,0.001418333,0.001536765,0.001109278,0.003585941],"category_scores_gemma":[0.003374439,0.0003169133,0.001212123,0.001755503,0.0004286185,0.002580796,0.0005593568,0.001080907,0.003061264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001062788,"about_ca_system_score_gemma":0.001258867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01083967,"about_ca_topic_score_gemma":0.01060112,"domain_scores_codex":[0.9991238,0.0001992771,0.00008226368,0.0002929413,0.000231632,0.00007010297],"domain_scores_gemma":[0.9986313,0.0008502454,0.00009031452,0.00008929946,0.0002900275,0.00004881661],"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":[0.0007975027,0.000714256,0.00960764,0.0006662984,0.0004376147,0.0006016377,0.0009052191,0.1868027,0.01685567,0.0547938,0.02719577,0.7006219],"study_design_scores_gemma":[0.00003046608,0.0001299135,0.001814503,0.00004360635,0.00008123712,0.0001655785,0.00004556912,0.9713082,0.002287682,0.0183696,0.005682827,0.00004085857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03496611,0.00137177,0.951268,0.001140389,0.0004132038,0.0004053568,0.002083736,0.003812009,0.004539489],"genre_scores_gemma":[0.566828,0.001936046,0.3984977,0.0008339687,0.0005006903,0.001020857,0.006551279,0.0003257296,0.02350585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01083967,"threshold_uncertainty_score":0.02155316,"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."}}