{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001795575,0.0005354066,0.0008464137,0.001724407,0.0004713062,0.001165124,0.001056932,0.001068148,0.002199278],"category_scores_gemma":[0.006967328,0.0002602147,0.000878119,0.001216137,0.0003178653,0.001773588,0.0004139399,0.001056769,0.00179488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001160139,"about_ca_system_score_gemma":0.001376586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01483398,"about_ca_topic_score_gemma":0.01069629,"domain_scores_codex":[0.9988139,0.0003275331,0.000102336,0.0003121675,0.0003546186,0.00008958808],"domain_scores_gemma":[0.9956735,0.002906199,0.0001960138,0.0002544122,0.000839536,0.0001304593],"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":[0.001744755,0.0009196413,0.01590413,0.0006540463,0.0002946329,0.0003648116,0.0003703933,0.1134657,0.02445914,0.003963219,0.01293637,0.8249232],"study_design_scores_gemma":[0.00004598331,0.0001929999,0.003438154,0.00003316361,0.00006103074,0.000148706,0.00004238893,0.9867159,0.006181827,0.001623211,0.001488917,0.00002769376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1538474,0.001187647,0.8259616,0.001206991,0.0004110569,0.0008215813,0.003179192,0.009982266,0.003402288],"genre_scores_gemma":[0.6417464,0.0006013308,0.3455542,0.0003325453,0.000145371,0.0004956438,0.005753186,0.0001547435,0.005216562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01483398,"threshold_uncertainty_score":0.0294953,"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."}}