{"id":"W2973188659","doi":"10.48550/arxiv.1909.04181","title":"BERT-Based Arabic Social Media Author Profiling","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Profiling (computer programming); Arabic; Social media; Computer science; Political science; World Wide Web; Linguistics; Philosophy; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008343813,0.0004236817,0.0004872875,0.0003577585,0.0003335477,0.0001929548,0.002240408,0.0006834188,0.00006347302],"category_scores_gemma":[0.0001625253,0.0004936352,0.0003837052,0.000793956,0.0001220815,0.0003346824,0.001481337,0.001214532,0.000469573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000349132,"about_ca_system_score_gemma":0.0008204642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001899162,"about_ca_topic_score_gemma":0.00001165468,"domain_scores_codex":[0.9970531,0.0003699138,0.0003089219,0.001403677,0.0002098074,0.0006545772],"domain_scores_gemma":[0.9976727,0.0003514667,0.0003999567,0.0010691,0.000265782,0.0002409645],"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":[0.00007586362,0.0001364836,0.007414686,0.0002965617,0.0001092178,0.0002480251,0.0009849862,0.1084975,0.0001365056,0.8803099,0.0007012235,0.001089061],"study_design_scores_gemma":[0.0008012124,0.000032743,0.002073696,0.0001144161,0.00008629359,0.000002239208,0.0001208143,0.9431542,0.001818907,0.04994693,0.0009127555,0.000935817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1230659,0.00005482812,0.871201,0.000573326,0.002049273,0.0004257635,0.00004545682,0.0005937982,0.001990597],"genre_scores_gemma":[0.9936055,0.000007786409,0.004724493,0.0002031965,0.0002305144,0.000001888094,0.0001063812,0.00002694146,0.001093297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8705396,"threshold_uncertainty_score":0.9997515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1485086942761924,"score_gpt":0.2271549994698412,"score_spread":0.07864630519364879,"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."}}