{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002028431,0.001632117,0.0006242266,0.001761813,0.0005145511,0.001119104,0.001074076,0.0008958371,0.002909848],"category_scores_gemma":[0.006806162,0.0003803192,0.0007212933,0.0009044326,0.0003626584,0.002287162,0.001480669,0.001940826,0.005570094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008278874,"about_ca_system_score_gemma":0.0008361381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007398863,"about_ca_topic_score_gemma":0.01385402,"domain_scores_codex":[0.9988936,0.0003653534,0.00005815479,0.0002771771,0.0002509037,0.0001549579],"domain_scores_gemma":[0.9966176,0.001210755,0.0002303926,0.0008480673,0.0008578619,0.0002352686],"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":[0.001414288,0.001053983,0.0811979,0.0004047691,0.0003045359,0.000528339,0.00104777,0.1276196,0.02448984,0.004406366,0.05774993,0.6997828],"study_design_scores_gemma":[0.00001888986,0.0001632829,0.01180912,0.00004233095,0.00003746311,0.0003193104,0.0002261925,0.9555572,0.01884095,0.004256692,0.008671627,0.00005697447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.625922,0.002175748,0.2955538,0.001937457,0.0009330586,0.0005369842,0.01911241,0.03655967,0.01726883],"genre_scores_gemma":[0.9035153,0.0003041484,0.0649175,0.0002287043,0.0001262911,0.0001716907,0.01835237,0.0003532779,0.01203069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007398863,"threshold_uncertainty_score":0.01471162,"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."}}