{"id":"W2108345839","doi":"10.1177/0165551508092257","title":"A hidden Markov model-based text classification of medical documents","year":2008,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Categorization; Artificial intelligence; Markov model; Subject (documents); Natural language processing; Machine learning; Markov chain; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973821,0.00008070636,0.0001516449,0.0008803965,0.0001757875,0.000139693,0.00260537,0.00007644366,0.00002679518],"category_scores_gemma":[0.0008385261,0.00006173714,0.00006665951,0.001406317,0.000503784,0.008477471,0.0001578012,0.0001743848,0.00002637882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109317,"about_ca_system_score_gemma":0.001463366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002425456,"about_ca_topic_score_gemma":2.220605e-7,"domain_scores_codex":[0.9963148,0.00002148631,0.000882838,0.00009451181,0.002518119,0.000168255],"domain_scores_gemma":[0.9973648,0.00006694795,0.001158411,0.0003889369,0.0008880211,0.0001328862],"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":[0.00005646573,0.0002634931,0.006424019,0.00005883891,0.00001831873,0.000007609636,0.004034898,0.001454269,0.007235628,0.250389,0.01043854,0.7196189],"study_design_scores_gemma":[0.0009463889,0.0001637839,0.03148461,0.00007038117,0.000004289027,0.0001324859,0.0003167702,0.944443,0.01732289,0.002605049,0.002349431,0.0001609241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09866388,0.0000210134,0.8929573,0.005431447,0.000211327,0.00007655611,8.048054e-7,0.00005021742,0.002587415],"genre_scores_gemma":[0.9134364,0.00007101661,0.08619491,0.0002584907,0.00001001175,0.000002624027,5.000563e-7,0.000001296882,0.00002478187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9429888,"threshold_uncertainty_score":0.6145962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02964063379902278,"score_gpt":0.2983874154971723,"score_spread":0.2687467816981495,"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."}}