How do neighborhood changes affect health? We analyzed how to use Google Street View to study changes in neighbourhood disorder.

For the attention of: Researchers worldwide measuring changes in built environment characteristics; Organizations that want to monitor the conditions of communities living environments; Community organizations advocating to have more Google Street View images for their neighbourhoods.

The problem: Previous studies have used Google Street View to measure different features of the built environment (e.g. street condition, walkability, housing external condition and so on), and it has shown to be a valid, faster, and cheaper method compared to in-person audit.

As Google Street View started in 2007, there is a possibility now to use longitudinal Google Street View images to test how neighborhoods change over time. However, few studies have used longitudinal Google Street View images, despite its high availability in some parts of the world.

What we did and why: We conducted a feasibility study exploring image availability over time in the Philadelphia metropolitan region and describing changes in neighbourhood disorder in this region between 2009, 2014, and 2019.

Our team audited Street View images from 192 street segments in the Philadelphia Metropolitan Region. On each segment, we measured the number of images available through time, and for locations where imagery from more than one-time point was available, we collected eight neighborhood disorder indicators at three different times (up to 2009, up to 2014, and up to 2019).

What our study adds: More than 70% of street segments had more than one image in Google Street View. Thus, there is high availability of images (especially in the Philadelphia city limits) which might allow researchers to test changes in the built environment with Google Street View.

Our neighbourhood disorder index slightly increased between 2009 and 2019 in those streets where we were able to test changes with Google Street View. Future studies should explore the determinants of these changes.

Implications for city policy and practice: Our finding that Google Street View Time Machine feature could reliably identify changes in neighbourhood disorder indicates that this approach could be used to monitor the built environment or assess the impacts of change over time.

While such monitoring is only feasible in areas with high spatio-temporal availability of images, researchers and public health officials that want to use Google Street View Time Machine feature could advocate for greater availability of images across more diverse contexts.

Full research article: Measuring changes in neighborhood disorder using Google Street View longitudinal imagery: a feasibility study by Pedro Gullon, Dustin Fry, Jesse J. Plascak, Stephen J. Mooney & Gina S. Lovasi.