{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007717822,0.00003840466,0.00008451216,0.00008545243,0.00003579799,0.00002416368,0.000255316,0.00003760742,0.00003020515],"category_scores_gemma":[0.0002878828,0.00003536914,0.00002213629,0.0003383825,0.00001906297,0.0001534363,0.00003894428,0.00004892544,0.00005048511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001534581,"about_ca_system_score_gemma":0.00002255356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003822063,"about_ca_topic_score_gemma":0.00001332049,"domain_scores_codex":[0.9993135,0.0001137485,0.0002275434,0.0001129694,0.000135597,0.00009665063],"domain_scores_gemma":[0.9995559,0.0001752243,0.00008278434,0.0001312418,0.00003366086,0.00002119056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.96418e-7,0.00003549113,0.001944598,0.00002909764,0.000002229918,3.379294e-7,0.003567009,0.00001339222,0.006466446,0.8833908,0.0002069221,0.1043427],"study_design_scores_gemma":[0.0003152362,0.00001442697,0.2233046,0.0000141152,0.00000265935,0.00000104529,0.00004636181,0.6302121,0.04816441,0.09765476,0.0001332028,0.0001371375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3019966,0.000009169578,0.6954324,0.0006451992,0.0002478326,0.00005498928,3.202263e-7,0.00008855527,0.001524908],"genre_scores_gemma":[0.9965912,5.711649e-7,0.003271307,0.00005077335,0.0000361012,0.000003774664,0.000001738301,0.000001596672,0.00004299353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.785736,"threshold_uncertainty_score":0.1442312,"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."}}