{"id":"W2284070151","doi":"","title":"What's in a Name? Using First Names as Features for Gender Inference in Twitter","year":2013,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":168,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Classifier (UML); Inference; Computer science; Artificial intelligence; Social media; Natural language processing; Baseline (sea); Information retrieval; Machine learning; 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":[0.0007564912,0.000221959,0.0002251841,0.0004307184,0.0001577659,0.0008565188,0.0007394249,0.0001806797,0.0003452779],"category_scores_gemma":[0.001184518,0.0002191452,0.00006773289,0.0006438184,0.00009315644,0.001575068,0.0001197377,0.0003809399,0.0003485966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224015,"about_ca_system_score_gemma":0.0004374832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002697832,"about_ca_topic_score_gemma":0.0003640529,"domain_scores_codex":[0.9977378,0.0001164857,0.0005473691,0.0005889277,0.0005698897,0.0004395349],"domain_scores_gemma":[0.9980236,0.0008139715,0.0001446928,0.0002376325,0.0006765059,0.0001036131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003038254,0.000120014,0.0006435221,0.00001765581,0.000005344865,0.000003860294,0.002334476,0.007276491,0.0005901304,0.9589701,0.00005722823,0.02995074],"study_design_scores_gemma":[0.00005930999,0.00005802558,0.003060196,0.0001343322,0.000001187667,0.000003195648,0.000715495,0.4526847,0.007317478,0.5355757,0.0001269691,0.0002633804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1411749,0.0001654101,0.842651,0.01142354,0.001181064,0.001256201,0.000008435592,0.0001093411,0.002030144],"genre_scores_gemma":[0.9894788,0.00003751522,0.008753578,0.001350547,0.00007497396,0.0001620183,0.000009792398,0.000009419875,0.0001233978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8483039,"threshold_uncertainty_score":0.8936483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2696613820475069,"score_gpt":0.4140428855734447,"score_spread":0.1443815035259378,"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."}}