{"id":"W2250104175","doi":"10.33011/lilt.v8i.1305","title":"Learning to Classify Documents According to Formal and Informal Style","year":2012,"lang":"en","type":"article","venue":"Linguistic Issues in Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Computer science; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Natural language processing; Style (visual arts); Sentence; Support vector machine; Machine learning; Computational linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004749146,0.0002117032,0.0002747174,0.0009191641,0.0001377348,0.0001271975,0.0009283981,0.0002199074,0.000009380886],"category_scores_gemma":[0.002530954,0.0002018237,0.00002107585,0.001036298,0.00005326336,0.0005216853,0.001636236,0.0005393191,0.00005627285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007519187,"about_ca_system_score_gemma":0.00001546042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001065559,"about_ca_topic_score_gemma":0.0000212321,"domain_scores_codex":[0.9982863,0.00002983203,0.0003080587,0.0003309236,0.0002027664,0.0008421271],"domain_scores_gemma":[0.9991863,0.00007173567,0.00008207387,0.0004426826,0.00006721108,0.000150026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003067076,0.0000736099,0.03665843,0.00009913178,0.00001765359,0.0001983348,0.06289019,0.00001254559,0.007355895,0.1901506,0.0001306016,0.7023823],"study_design_scores_gemma":[0.005692721,0.006079571,0.01366941,0.003506302,0.0001313538,0.002003302,0.0947721,0.02061866,0.5338814,0.05836293,0.251834,0.009448254],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8205098,0.00552688,0.1640712,0.001410158,0.0007320725,0.0006023498,0.000001893803,0.002846834,0.004298827],"genre_scores_gemma":[0.6607935,0.000006443779,0.3384751,0.0003169666,0.0001288714,0.00003630544,0.000001445135,0.00001250805,0.0002288797],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6929341,"threshold_uncertainty_score":0.823013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00676897105367181,"score_gpt":0.307116565836935,"score_spread":0.3003475947832632,"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."}}