{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005854512,0.0005203129,0.0004604027,0.001597268,0.0006488258,0.0005655152,0.0006988964,0.0005564364,0.001839721],"category_scores_gemma":[0.002529927,0.0002394055,0.000665409,0.001621168,0.0001492532,0.0007468477,0.001133091,0.0005437181,0.002053178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005374879,"about_ca_system_score_gemma":0.0006402071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02564672,"about_ca_topic_score_gemma":0.05594429,"domain_scores_codex":[0.9993881,0.000113818,0.00009877682,0.0002230328,0.0001197745,0.00005658957],"domain_scores_gemma":[0.999141,0.0001536891,0.0001262941,0.0002320802,0.000270704,0.0000761898],"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":[0.0008647492,0.0006876612,0.5399413,0.001521769,0.0006014545,0.001205886,0.00169394,0.01759139,0.01513634,0.002773125,0.2657547,0.1522277],"study_design_scores_gemma":[0.0002287682,0.000459858,0.6072379,0.0003709134,0.0003091516,0.0007432215,0.003456497,0.1728561,0.01096491,0.003856663,0.1993252,0.0001907271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.4170676,0.0004610916,0.01874896,0.0007787498,0.0002779784,0.0008222273,0.5506464,0.003888398,0.007308701],"genre_scores_gemma":[0.2288119,0.0002212745,0.04456564,0.0001603408,0.00006686472,0.001255047,0.7225411,0.0001510044,0.002226841],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02564672,"threshold_uncertainty_score":0.05099487,"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."}}