{"id":"W2565143233","doi":"10.82308/24058","title":"Text classification using a hidden Markov model","year":2005,"lang":"en","type":"article","venue":"Open MIND","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Artificial intelligence; Categorization; Natural language processing; Naive Bayes classifier; Test set; Machine learning; Bayesian probability; Pattern recognition (psychology); Data mining; Support vector machine","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":[0.0002081815,0.0000949721,0.00009847583,0.00009685952,0.0001273126,0.0005679911,0.001769485,0.00007293355,0.000223995],"category_scores_gemma":[0.0000250458,0.0000886282,0.00002812973,0.0002743124,0.00004246837,0.001419895,0.0005240783,0.00007121642,0.0005185076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008764882,"about_ca_system_score_gemma":0.0001007069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005484699,"about_ca_topic_score_gemma":0.00001060062,"domain_scores_codex":[0.9990749,0.00001994044,0.00020084,0.0003678082,0.0001598009,0.0001767377],"domain_scores_gemma":[0.9990765,0.00002072482,0.0001152144,0.0006989256,0.00004513974,0.00004348048],"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":[0.000002303755,0.00003854134,0.00007064388,6.141341e-7,0.000003598706,4.401801e-7,0.000210337,0.0001012404,0.00832504,0.007073171,0.001070918,0.9831032],"study_design_scores_gemma":[0.0001904228,0.00001148432,0.000344016,0.000007776598,0.000004308039,0.000004592882,0.0001011083,0.9517657,0.0113096,0.001681125,0.03442672,0.0001531465],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1335999,0.00007454054,0.7910529,0.01028461,0.00009083661,0.0004633709,0.00000393467,0.00005990139,0.06436995],"genre_scores_gemma":[0.5110346,0.000004978828,0.4858077,0.0000560757,0.00001554796,0.00001035217,0.000001814144,0.000003642936,0.003065252],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.98295,"threshold_uncertainty_score":0.6664538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1071301472310728,"score_gpt":0.3418787696192839,"score_spread":0.2347486223882111,"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."}}