While previous studies have found that Twitter can be used to track the spread of illnesses, researchers now say that they can use Facebook to predict obesity rates in cities, and even in neighbourhoods, based on the interests listed on the profile pages of the people living in particular localities.
Scientists from Boston Children’s Hospital in the US found that people’s online interests, when studied according to geographic areas, could help public health researchers track and map obesity rates, and design geo-targeted online interventions to reduce the risks. For example, areas where Facebook users ‘liked’ pages related to television were more likely to have high rates of obesity compared to areas whose residents, liked, activity-related pages.
To reach their findings, the research team obtained aggregated Facebook user interest data, what users post to their timeline, like and share with others on Facebook, from users
within the US and just within New York City.
Using two prior telephone-based health surveys involving thousands of people, they then compared percentages of users interested in healthy activities or television. Both surveys record geo-tagged data on body mass index, which researchers consider a reliable measure of obesity.
"The data shows that in places where Facebook users have more activity-related interests, there is a lower prevalence of obesity,” says co-researcher Dr Rumi Chunara. “They reveal how social media data can augment public health surveillance by giving public health researchers access to population-level information that they can’t otherwise get.”