{"id":"W3210547737","doi":"10.5281/zenodo.4434972","title":"A Geo-Tagged COVID-19 Twitter Dataset for 10 North American Metropolitan Areas","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Metropolitan area; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Geography; 2019-20 coronavirus outbreak; Cartography; Outbreak; Biology; Virology; Medicine; Archaeology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005607784,0.001629867,0.0008217319,0.0024061,0.0009094302,0.0009882405,0.001560972,0.001383619,0.01107686],"category_scores_gemma":[0.001923218,0.000396602,0.0007714825,0.003995091,0.0003387367,0.0009076072,0.001430084,0.001159631,0.01691084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001633053,"about_ca_system_score_gemma":0.002117248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.09605044,"about_ca_topic_score_gemma":0.1777507,"domain_scores_codex":[0.9994254,0.00009806518,0.00006110936,0.000144771,0.0001784792,0.00009218628],"domain_scores_gemma":[0.9990755,0.0001598422,0.00008781464,0.0001817467,0.0003457257,0.0001493549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008251372,0.00006488465,0.003429845,0.0003947579,0.00003791577,0.00007631301,0.00005958342,0.001273482,0.0005911291,0.0005096948,0.9883375,0.005142446],"study_design_scores_gemma":[0.0001981232,0.00006648401,0.03862526,0.0002732263,0.00006492033,0.0002149527,0.0005302985,0.01052829,0.001796063,0.001718467,0.9458933,0.00009057404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002081397,0.00008625948,0.0002143587,0.0001854959,0.00006628051,0.00003592512,0.9957423,0.0006116173,0.0009763662],"genre_scores_gemma":[0.001410844,0.00004516773,0.0003815952,0.00004439036,0.000009958892,0.00006589106,0.9974469,0.00002505292,0.0005703073],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09605044,"threshold_uncertainty_score":0.1909828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0551154648384589,"score_gpt":0.3239826475311255,"score_spread":0.2688671826926666,"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."}}