{"id":"W2560620367","doi":"10.29173/cais341","title":"A Comparative Study on Feature Selection of Text Categorization for Hidden Markov Models","year":2013,"lang":"fr","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":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Selection (genetic algorithm); Feature selection; Categorization; Context (archaeology); Artificial intelligence; Computer science; Humanities; Natural language processing; Geography; Philosophy","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":[0.008279926,0.0008673027,0.0009543406,0.002018493,0.0004821128,0.001289866,0.0007398373,0.0009830531,0.001574956],"category_scores_gemma":[0.02684334,0.0002555153,0.00103231,0.00167727,0.0003479129,0.002648062,0.0005168521,0.000781778,0.0005001049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001058953,"about_ca_system_score_gemma":0.0005297998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005979876,"about_ca_topic_score_gemma":0.004510527,"domain_scores_codex":[0.9962605,0.002381653,0.000237683,0.0003923337,0.0005705755,0.0001573467],"domain_scores_gemma":[0.9652529,0.03152576,0.0004890289,0.0008345313,0.001720392,0.0001773554],"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":[0.002864528,0.0006088385,0.02832859,0.0007536192,0.0005319939,0.0003042138,0.0008238991,0.09208485,0.01024491,0.005061903,0.003420104,0.8549726],"study_design_scores_gemma":[0.00007783564,0.001156588,0.02280831,0.000117866,0.0002143429,0.0002611603,0.0005749819,0.9603394,0.00669812,0.004623089,0.003068874,0.00005942287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5345042,0.01497996,0.4378489,0.001440773,0.0002347169,0.0003639737,0.0005907484,0.002643418,0.007393302],"genre_scores_gemma":[0.9213942,0.001615598,0.07461892,0.00009399039,0.00009956244,0.0001248783,0.0007965519,0.0001107338,0.00114551],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008279926,"threshold_uncertainty_score":0.04378891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05343692366918243,"score_gpt":0.2833853176220592,"score_spread":0.2299483939528768,"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."}}