{"id":"W2783314643","doi":"10.1109/bigdata.2017.8258240","title":"Language identification in multilingual, short and noisy texts using common N-grams","year":2017,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Correctness; Language identification; Artificial intelligence; Natural language processing; Naive Bayes classifier; Support vector machine; Classifier (UML); Artificial neural network; Identification (biology); Natural language; Task (project management); Random forest; Machine learning; Algorithm","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":[0.0005780835,0.00007136074,0.00009556804,0.00006083378,0.0002815018,0.0004248401,0.0004503439,0.00005558861,0.000007603514],"category_scores_gemma":[0.00008498794,0.00006689758,0.0000179372,0.00006484216,0.00004912318,0.0005136085,0.0002212901,0.0001038681,0.0000120201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002291603,"about_ca_system_score_gemma":0.00001705743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003220589,"about_ca_topic_score_gemma":0.0003011712,"domain_scores_codex":[0.9992807,0.00004410299,0.000175627,0.0002373817,0.0001115373,0.0001506583],"domain_scores_gemma":[0.9992813,0.00003086069,0.00006676128,0.0005422239,0.000026649,0.00005224225],"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":[0.00001323529,0.0001313579,0.2988732,0.00005241253,0.0000134542,0.00009134159,0.00792797,0.0001172043,0.08880457,0.04456476,0.00004275506,0.5593678],"study_design_scores_gemma":[0.0003346994,0.00001600611,0.3098169,0.00004869327,0.000004947295,0.00002200521,0.0002376655,0.6109456,0.0764182,0.001633762,0.0002407818,0.0002807583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8793425,0.0001258936,0.119491,0.0002765268,0.0001672962,0.0001021512,9.237813e-7,0.00006196438,0.0004317658],"genre_scores_gemma":[0.9913473,0.000005048362,0.008331419,0.00009122815,0.00002397537,0.00000213533,0.000002719709,0.000003706295,0.0001925335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6108284,"threshold_uncertainty_score":0.4096743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06960196406045646,"score_gpt":0.3813035576215925,"score_spread":0.311701593561136,"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."}}