{"id":"W1997305228","doi":"10.1109/nlpke.2010.5587767","title":"Automatic classification of documents by formality","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formality; Computer science; Naive Bayes classifier; Artificial intelligence; Feature selection; Classifier (UML); Support vector machine; Machine learning; Decision tree; Task (project management); Style (visual arts); Data mining; Natural language processing; Engineering","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":[0.0001966331,0.00006472514,0.00008244859,0.0000653203,0.00004533733,0.00006487712,0.000809258,0.00006734557,0.0001627271],"category_scores_gemma":[0.0000509823,0.00005233012,0.00002959484,0.0002314934,0.0000678534,0.0007026963,0.0001180665,0.00009331443,0.00006398232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009688242,"about_ca_system_score_gemma":0.00002105556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435847,"about_ca_topic_score_gemma":0.000005142414,"domain_scores_codex":[0.9992801,0.00001189214,0.0002368409,0.0001674904,0.0001862287,0.0001174461],"domain_scores_gemma":[0.9990735,0.00003582803,0.0001405111,0.0006668997,0.00005240953,0.00003085379],"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":[3.388631e-7,0.00005873408,0.00234162,0.00000768875,0.000003952166,4.678316e-8,0.00004432114,4.087409e-8,0.1432511,0.6935045,0.008083038,0.1527046],"study_design_scores_gemma":[0.0005884039,0.00009949904,0.1620238,0.000008327847,0.000007644092,0.00000461413,0.0001565116,0.08397029,0.6330305,0.0816893,0.03806393,0.0003571843],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5423102,0.00001550898,0.4282617,0.004654074,0.000331241,0.0002125033,0.000002427867,0.001136617,0.02307563],"genre_scores_gemma":[0.9631925,0.000003484185,0.03603388,0.0000486146,0.000003667971,0.00001814414,0.000003362859,0.000002168184,0.0006941524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6118152,"threshold_uncertainty_score":0.213396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01347406047579485,"score_gpt":0.2704840205753174,"score_spread":0.2570099600995225,"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."}}