{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001675898,0.0006039946,0.0007310807,0.005768349,0.0009220176,0.001782772,0.0004919464,0.000823525,0.001052827],"category_scores_gemma":[0.0120945,0.0001787521,0.0003815588,0.003772342,0.0006064762,0.003407255,0.001296968,0.0006947092,0.001263112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005468459,"about_ca_system_score_gemma":0.00050313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001288364,"about_ca_topic_score_gemma":0.003205209,"domain_scores_codex":[0.9975951,0.0008674213,0.0002915876,0.0005471906,0.0005381115,0.000160487],"domain_scores_gemma":[0.9905142,0.00552384,0.001645919,0.0007929142,0.001223781,0.0002994635],"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":[0.001352332,0.0004426219,0.1055469,0.001021519,0.0002025091,0.001780983,0.004347371,0.01321207,0.05960755,0.007700883,0.006259421,0.7985259],"study_design_scores_gemma":[0.00006171628,0.000601638,0.1100767,0.0005013311,0.000202935,0.002829617,0.007654742,0.6770831,0.1194793,0.04703365,0.0342374,0.000237842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7546535,0.001706145,0.2327256,0.0006270093,0.0002004292,0.0001921223,0.002301933,0.002721399,0.004871864],"genre_scores_gemma":[0.8694361,0.0003545388,0.1245837,0.00006669401,0.00009226368,0.00007918312,0.002779864,0.0001763778,0.002431368],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005768349,"threshold_uncertainty_score":0.008863151,"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."}}