{"id":"W3036302882","doi":"10.4081/gh.2020.882","title":"Use of Twitter social media activity as a proxy for human mobility to predict the spatiotemporal spread of COVID-19 at global scale","year":2020,"lang":"en","type":"article","venue":"Geospatial health","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Outbreak; Social media; Coronavirus disease 2019 (COVID-19); Mainland China; Cohort; China; Proxy (statistics); Geography; Demography; Preparedness; Medicine; Infectious disease (medical specialty); Disease; Statistics; Computer science; Virology; Political science; Internal medicine","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":[0.0005022013,0.000485544,0.000232425,0.001950766,0.0002355577,0.0007118331,0.000298015,0.0003325678,0.001175433],"category_scores_gemma":[0.002559733,0.0001723431,0.0004414826,0.001458192,0.0001902092,0.0009343295,0.0006553037,0.0003663136,0.0005011227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003694475,"about_ca_system_score_gemma":0.0003365854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01326058,"about_ca_topic_score_gemma":0.01783661,"domain_scores_codex":[0.9997301,0.00006658773,0.00003575794,0.00008097696,0.0000394271,0.00004721538],"domain_scores_gemma":[0.998776,0.0003119584,0.0005366671,0.00007794721,0.0001422555,0.0001551488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009897851,0.00002616848,0.9895663,0.00004183761,0.00007614552,0.00009605282,0.0001273103,0.00170736,0.0004786541,0.0001395648,0.0008398723,0.006801766],"study_design_scores_gemma":[0.00001674357,0.0001201504,0.9328951,0.0000599879,0.0001184984,0.0002424476,0.0008237796,0.06202981,0.0006684821,0.0004318672,0.0025669,0.00002623093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989967,0.000235985,0.001071019,0.0001922314,0.00002754206,0.00004234421,0.006872728,0.00005923144,0.001532018],"genre_scores_gemma":[0.9940093,0.0001593987,0.0009374743,0.00002776564,0.00002965171,0.00004103041,0.004494477,0.00000560604,0.0002953629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01326058,"threshold_uncertainty_score":0.02636677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3829462630222863,"score_gpt":0.4783105237812297,"score_spread":0.09536426075894339,"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."}}