Quantifying Scenic Areas Using Crowdsourced Data
Seresinhe, C. I., Moat, H. S., & Preis, T. (2018) Environment and Planning B: Urban Analytics and City Science, 45(3), 567-582.
Our results provide evidence that by exploiting the vast quantity of data generated on the Internet, scientists and policy-makers may be able to develop a better understanding of people's subjective experience of the environment in which they live.
For centuries, philosophers, policy-makers and urban planners have debated whether aesthetically pleasing surroundings can improve our wellbeing. To date, quantifying how scenic an area is has proved challenging, due to the difficulty of gathering large-scale measurements of scenicness.
In this study we ask whether images uploaded to the website Flickr, combined with crowdsourced geographic data from OpenStreetMap, can help us estimate how scenic people consider an area to be. We validate our findings using crowdsourced data from Scenic-Or-Not, a website where users rate the scenicness of photos from all around Great Britain.
We find that models including crowdsourced data from Flickr and OpenStreetMap can generate more accurate estimates of scenicness than models that consider only basic census measurements such as population density or whether an area is urban or rural.