{"id":"W2103195385","doi":"10.1145/2632188.2632207","title":"Automatic identification of arabic dialects in social media","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Arabic; Classifier (UML); Hidden Markov model; Naive Bayes classifier; Modern Standard Arabic; Social media; Language identification; Context (archaeology); Probabilistic logic; n-gram; Language model; Linguistics; Natural language; Support vector machine; World Wide Web","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":[0.0008734317,0.0006868309,0.0004299079,0.004536909,0.000746098,0.001469307,0.0003643997,0.0006106441,0.00232403],"category_scores_gemma":[0.003553954,0.0001848973,0.0004024227,0.001637361,0.0002741011,0.001743803,0.001002388,0.0005318662,0.003852466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004524586,"about_ca_system_score_gemma":0.0004185596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003409623,"about_ca_topic_score_gemma":0.004765383,"domain_scores_codex":[0.9990131,0.0003586413,0.0000828594,0.0002269874,0.0002045674,0.0001138389],"domain_scores_gemma":[0.9974664,0.0008349915,0.0003437668,0.000274662,0.0009409044,0.0001392497],"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":[0.001085771,0.0003988144,0.1164774,0.0007309649,0.0001566386,0.001437275,0.004093414,0.003169986,0.07751209,0.004073606,0.03771956,0.7531444],"study_design_scores_gemma":[0.00007399413,0.0004074427,0.2723301,0.0004146614,0.0002284531,0.003213195,0.01536625,0.4871541,0.1051296,0.01567825,0.09974212,0.0002619048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.866618,0.001873542,0.0951743,0.001342794,0.0006337159,0.0004541253,0.01267966,0.006055143,0.01516864],"genre_scores_gemma":[0.9024004,0.0005617341,0.07971725,0.0001848336,0.0002078554,0.0001427005,0.009659707,0.0001506278,0.006974859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004536909,"threshold_uncertainty_score":0.007774711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03165082704362224,"score_gpt":0.2818454130505005,"score_spread":0.2501945860068783,"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."}}