Big Data Meets Survey Science

15Assessing Community Wellbeing Using Google Street‐View and Satellite Imagery

Pablo Diego‐Rosell, Stafford Nichols, Rajesh Srinivasan, and Ben Dilday

The Gallup Organization, Washington, DC, USA

15.1 Introduction

American communities face significant health and wellbeing challenges. In addition to long‐standing inequalities among minorities, mortality and morbidity rates have increased among whites since the turn of the century (Case and Deaton 2015). Increases in drug overdoses, suicides, and alcohol‐related liver disease are mostly to blame for this ongoing trend (Case and Deaton 2017). Community health data in the United States are collected through expensive large‐scale surveys, including the American Community Survey (ACS) and the behavioral risk factor surveillance system (BRFSS). Additionally, Gallup conducts a cross‐sectional Daily Tracking survey (GDT) that covers both subjective wellbeing (SWB) and self‐reported health variables. These data sources collect data relatively infrequently: smaller regions are only surveyed every three or five years in the ACS, and with much lower coverage at the community level in the BRFSS and GDT.

Over the last decade, computational methods have progressed remarkably, and deep learning applications are now able to leverage text data from social media and different types of satellite and panoramic imagery to reliably estimate statistics relating to race, gender, education, occupation, unemployment, and other demographics at the small‐area ...