{"id":"W2250194349","doi":"10.18653/v1/d13-1114","title":"Gender Inference of Twitter Users in Non-English Contexts","year":2013,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Public Safety Canada","keywords":"Inference; Computer science; Orthography; Natural language processing; Social media; Artificial intelligence; Data science; Linguistics; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002205355,0.00006690097,0.0001061987,0.00007729817,0.00001802109,0.00004982403,0.0003814931,0.00005279855,0.0002994787],"category_scores_gemma":[0.00007982866,0.00005575074,0.00002667136,0.0002491148,0.00002589838,0.0004742309,0.000125589,0.0001075363,0.000143659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001467069,"about_ca_system_score_gemma":0.00004721198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671888,"about_ca_topic_score_gemma":0.00001061396,"domain_scores_codex":[0.9992994,0.0000412744,0.0001928363,0.0001666478,0.0001261118,0.0001737402],"domain_scores_gemma":[0.9994141,0.00008393952,0.00004704237,0.0002463966,0.0001518343,0.000056619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007405512,0.0001588889,0.5918897,0.0000729868,0.00002591508,0.00000813286,0.02360607,0.0002297304,0.005180593,0.3428503,0.008530436,0.02743978],"study_design_scores_gemma":[0.001225585,0.00008615777,0.8529966,0.00005761323,0.000003170776,0.000001976052,0.0008574027,0.08881617,0.03298506,0.02066654,0.001776726,0.0005269443],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4039092,0.00001748096,0.576124,0.0003786599,0.0002757159,0.0001780399,3.975521e-7,0.00006621695,0.01905032],"genre_scores_gemma":[0.9901167,0.000001830925,0.008836996,0.0006408455,0.00001429373,0.000009330334,7.020573e-7,0.000002310373,0.0003770276],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5862074,"threshold_uncertainty_score":0.3279082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04556533857021437,"score_gpt":0.2934247514939073,"score_spread":0.2478594129236929,"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."}}