{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004470607,0.0003418046,0.000651596,0.0002790145,0.0001732617,0.002121586,0.002115882,0.0002775675,0.00002156276],"category_scores_gemma":[0.002992935,0.0002753196,0.0001745812,0.0009293886,0.000458749,0.01333787,0.0004872727,0.0003200989,0.000004456276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018294,"about_ca_system_score_gemma":0.0002789598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002952468,"about_ca_topic_score_gemma":0.00001603214,"domain_scores_codex":[0.9978974,0.00004747089,0.0006270619,0.0005011224,0.0005341867,0.0003927815],"domain_scores_gemma":[0.9511524,0.0002110896,0.001384037,0.0002782354,0.04689792,0.00007628708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004520519,0.002674541,0.06023939,0.00107936,0.0005618554,2.947426e-7,0.1846645,0.0001030897,0.04745297,0.5816901,0.04308281,0.07799906],"study_design_scores_gemma":[0.003521153,0.008070682,0.2554214,0.001204852,0.0004725305,0.00002447392,0.05760657,0.1276561,0.3455783,0.1863139,0.01280447,0.001325506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756039,0.0002581701,0.00557628,0.01169473,0.0003502847,0.002571365,0.0001057608,0.0001079065,0.003731604],"genre_scores_gemma":[0.9921963,0.00006040029,0.003711794,0.00005716179,0.00005611834,0.0002296845,0.000004449443,0.0000174486,0.003666629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3953761,"threshold_uncertainty_score":0.9999699,"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."}}