{"id":"W2788623952","doi":"10.1177/1536867x1801700406","title":"Text Mining with n-gram Variables","year":2017,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit van Tilburg; University of Waterloo","keywords":"n-gram; Computer science; Gram; Categorization; Process (computing); Text categorization; Natural language processing; Sequence (biology); Artificial intelligence; Language model; Programming language","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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001340424,0.0001653058,0.0001728829,0.00006359065,0.005596771,0.00297212,0.005000227,0.00002563623,0.000006441417],"category_scores_gemma":[0.0004306071,0.0001070665,0.00001804209,0.0001125478,0.0004475929,0.0005660434,0.00140044,0.000495941,0.000009972704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002314581,"about_ca_system_score_gemma":0.0001382932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009771233,"about_ca_topic_score_gemma":0.00005165714,"domain_scores_codex":[0.9986582,0.0001617026,0.0003338445,0.000258574,0.0002936679,0.0002939923],"domain_scores_gemma":[0.9939488,0.0009198689,0.0005760848,0.004188861,0.000218263,0.0001481651],"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":[0.000009271261,0.0001566339,0.0003255789,0.00001353053,0.00008170773,0.0000143046,0.002541203,0.00002204602,0.00002309939,0.4389641,0.005948241,0.5519003],"study_design_scores_gemma":[0.001414859,0.0008440493,0.01327568,0.0004991471,0.0001186916,0.0007820473,0.001366394,0.8058097,0.00004400919,0.08010905,0.09501202,0.0007243751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001978051,0.0002012357,0.9847111,0.009860522,0.00007008961,0.000201636,0.0006078433,0.00004832127,0.002321274],"genre_scores_gemma":[0.2202826,0.0008589675,0.7783625,0.0001656641,0.00003987955,0.00002042162,0.00004889255,0.00001857632,0.0002026049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8057876,"threshold_uncertainty_score":0.9980629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0460079612838921,"score_gpt":0.321158498507218,"score_spread":0.2751505372233259,"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."}}