Over a million developers have joined DZone.

Can Facebook predict the obesity of a town?

DZone 's Guide to

Can Facebook predict the obesity of a town?

· ·
Free Resource

With the realms of data available on the web, the number of uses for that data continues to rise.  Last week we saw researchers claim that they could predict stock movements based upon the keywords entered into Google.

This week researchers believe they have unlocked the key to understanding the obesity of an area.  The team, from Boston Children’s Hospital, believe that the kind of things people like on Facebook can provide telling insight into the overall health levels of that area.

For instance if a high percentage of Facebook users cite exercise amongst their list of interests, they believe that will be replicated in a lower obesity rate for the entire town.  The flip side is that if people cite things like watching television amongst their interests, it will see higher obesity rates.

“Online social networks like Facebook represent a new high-value, low-cost data stream for looking at health at a population level,” according to researcher John Brownstein, who runs the Computational Epidemiology Group within CHIP. “The tight correlation between Facebook users’ interests and obesity data suggest that this kind of social network analysis could help generate real-time estimates of obesity levels in an area, help target public health campaigns that would promote healthy behavior change, and assess the success of those campaigns.”

The researchers obtained aggregated data containing users interests, their timeline posts and what they liked on the social network.  The sample consisted of people from across America, and also from purely within New York.

Analysing this data allowed them to compare the percentage of people with healthy and sedentary Facebook content with data from two surveys that recorded geotagged data on body mass index.

The analysis revealed that the closest correlation was between the interests people declared on Facebook and the obesity rates in their town.  For instance, obesity rates were 12% lower in the area that had the highest percentage of Facebook users having exercise related activities.

What’s more, the correlation also worked on a more local level, with specific areas of New York showing lower obesity rates when residents revealed active interests on Facebook.

Relating proportion of activity-related “likes”
on Facebook with obesity rates

Region with lowest percentage Region with highest percentage ? obesity rate between lowest and highest
Nationally Kansas City, Mo.-Kan. (1.3%) Coeur d’Alene, Idaho (25.4%) -12%
NYC Southwest Queens (7.6%) Coney Island

Relating proportion of television-related “likes”
on Facebook with obesity rates

Region with lowest percentage Region with highest percentage ? obesity rate between lowest and highest
Nationally Eugene-Springfield, Ore. (50.3%) Myrtle Beach-Conway-North Myrtle Beach, S.C. (76%) +3.9%
NYC Greenpoint (64%) Northeast Bronx (70.6%) +27.5%

 ”The data show that in places where Facebook users have more activity-related interests, there is a lower prevalence of obesity and overweight,” said Chunara, an instructor in Brownstein’s group. “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.”

The study also bolsters the case for using social media as a means of delivering targeted interventions aimed at reducing rates of obesity and other chronic diseases, as applicable.


Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}