• by Erik Sass , Staff Writer @eriksass1, November 1, 2016

While the primary purpose is obviously to make our friends jealous, it turns out all those beautiful photos posted on social media sites have some other applications as well. One of the more interesting uses is as a source of data for scientists and policymakers studying land use, development, and conservation.

A paper titled “Continental-scale quantification of landscape values using social media data” and published in the Proceedings of the National Academy of Sciences, describes a new technique that analyzes geotagged photos (including comments) from social media sites to create predictive models that can help guide complex decisions about how to use public lands.

The researchers aggregated social media posts containing geotagged photos of natural landscapes in Europe, including landmarks and scenic attractions, from Instagram, Flickr, and Panoramio, to determine how observers and their social networks react to various features. They then sorted the geotagged locations into four tiers of more- and less-visited spots, and mapped and analyzed them with algorithms to find common elements in popular destinations.

Among other patterns that stood out, the algorithms found that the most favored landscapes were those including mountains, rivers and lakes, as well as those near big population centers (suggesting accessibility plays a large part in their popularity).

This data in turn can inform policy making about land use decisions in order to produce the maximum economic benefit – for example, when deciding whether to keep an Alpine meadow for cattle grazing or turn it into a ski resort.

In their abstract the authors note the changes that prompted the research: “In many landscapes across the globe, we are witnessing an ongoing functional shift away from landscapes managed for extractive activities (e.g., agriculture, mining, forestry) and toward landscapes managed for recreation and leisure activities.” With that in mind, they go on, “Social media data… can be used to indirectly measure and identify valuable features of landscapes at a regional, continental, and perhaps even worldwide scale.”