{"id":"W2536458098","doi":"10.2196/publichealth.5869","title":"Building a National Neighborhood Dataset From Geotagged Twitter Data for Indicators of Happiness, Diet, and Physical Activity","year":2016,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Environmental Health Sciences; Centers for Disease Control and Prevention; National Institutes of Health; Utah Department of Health","keywords":"Happiness; Social media; Health data; Data science; Geography; Environmental health; Computer science; Psychology; World Wide Web; Medicine; Political science; Health care; Social psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00134625,0.0000948363,0.000259369,0.00005318713,0.0002742962,0.00005285257,0.000290771,0.00005772951,0.00001706193],"category_scores_gemma":[0.0004331527,0.00006775827,0.00001962904,0.0001936984,0.0003065997,0.0005961512,0.00008259514,0.00006678901,4.254339e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003599615,"about_ca_system_score_gemma":0.0007085194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0010802,"about_ca_topic_score_gemma":0.001001516,"domain_scores_codex":[0.9986162,0.0001526355,0.0001827373,0.0004201276,0.0002997678,0.0003285169],"domain_scores_gemma":[0.9986316,0.0005445835,0.0001833335,0.0002748822,0.00005901171,0.0003066165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008574962,0.0001630191,0.9453456,0.0000752657,0.00001863493,1.748282e-7,0.0008231638,7.367111e-9,0.00002919213,0.001657409,0.007865147,0.04393662],"study_design_scores_gemma":[0.0006410245,0.00004504786,0.8244895,0.00001112581,7.087918e-7,4.479013e-8,0.00008579975,0.00009305389,0.000001863364,0.002088113,0.1724306,0.0001130826],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713584,0.0001395337,0.001543423,0.01669406,0.00006852105,0.0003921697,0.009674273,0.0000240018,0.0001055843],"genre_scores_gemma":[0.9983047,0.00006050466,0.0001704032,0.0003255102,0.00026721,0.00003284461,0.000817207,0.000005792357,0.00001578507],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1645655,"threshold_uncertainty_score":0.2763102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07284615749997338,"score_gpt":0.3838573703680377,"score_spread":0.3110112128680643,"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."}}