{"id":"W2251433042","doi":"10.3115/v1/w14-5904","title":"Automatic Identification of Arabic Language Varieties and Dialects in Social Media","year":2014,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Arabic; Computer science; Identification (biology); Natural language processing; Social media; Language identification; Linguistics; Artificial intelligence; Natural language; World Wide Web; Botany","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":[0.0005985352,0.00003657915,0.00007804584,0.00006591412,0.00003636081,0.00003320113,0.0001313435,0.0000342019,0.00001483933],"category_scores_gemma":[0.0002158419,0.00003282684,0.00001139274,0.0001800882,0.00002983721,0.0001350854,0.00004327439,0.00004242925,0.000007857997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007361419,"about_ca_system_score_gemma":0.00001332793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001025789,"about_ca_topic_score_gemma":0.00002312639,"domain_scores_codex":[0.9994767,0.00009281488,0.0001573857,0.0000984178,0.0000990163,0.00007568901],"domain_scores_gemma":[0.9996451,0.0001666841,0.00005830095,0.0000917605,0.00002008665,0.00001811251],"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":[0.000001608596,0.00002499004,0.002692583,0.00006307833,0.00000331345,6.736884e-7,0.02794758,0.000003698021,0.009705025,0.8734931,0.00009503261,0.08596925],"study_design_scores_gemma":[0.000508209,0.00002808967,0.4067477,0.00001990227,0.000006199344,0.000003081491,0.0007042645,0.4361685,0.05490325,0.1006279,0.00006679268,0.0002161238],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6319823,0.00004221478,0.3666908,0.0003863426,0.0001099523,0.00004478879,4.491545e-7,0.00006265768,0.0006804711],"genre_scores_gemma":[0.9976742,0.000001416254,0.002205154,0.00003997825,0.00002416253,0.000002758614,0.000001689475,0.000001454991,0.00004923321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7728653,"threshold_uncertainty_score":0.133864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806990496924178,"score_gpt":0.2669399753216908,"score_spread":0.248870070352449,"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."}}