{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005160025,0.001429343,0.001564162,0.006217979,0.00142162,0.003701447,0.001624182,0.001323207,0.006026517],"category_scores_gemma":[0.04114822,0.0005633192,0.001533166,0.007900179,0.001031924,0.005220482,0.002734909,0.002487924,0.005974269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007204709,"about_ca_system_score_gemma":0.001751152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001481897,"about_ca_topic_score_gemma":0.002023668,"domain_scores_codex":[0.9921432,0.003183762,0.0009517304,0.0018382,0.001644683,0.0002384357],"domain_scores_gemma":[0.9819826,0.01360634,0.001247119,0.001520518,0.001377014,0.0002664071],"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":[0.0008850031,0.0003006297,0.0154148,0.001604955,0.0005513529,0.0009071359,0.001402077,0.03062224,0.007183612,0.0464173,0.05641392,0.8382971],"study_design_scores_gemma":[0.0001855251,0.0003360218,0.006714109,0.0006168091,0.0002508791,0.0009986997,0.001143312,0.5114467,0.01571054,0.3515945,0.1108223,0.0001806904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01234882,0.001278711,0.9649223,0.001203266,0.000277453,0.0004946763,0.007681304,0.009060456,0.002733049],"genre_scores_gemma":[0.115126,0.001118867,0.86307,0.0006116396,0.0004523655,0.001165597,0.01494509,0.0006027891,0.002907686],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006217979,"threshold_uncertainty_score":0.02728909,"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."}}