It’s believed that around 80 million images are added to Instagram each and every day.  A recent study suggests that this vast amount of data could yield fascinating insights into the habits of users.

A team from the University of Rochester have been trawling through the images shared on Instagram for insights into the drinking habits of teenagers.  They believe that their algorithms can provide a better, and cheaper, means of detecting teenage drinking than more traditional methods.

Underage drinking

As Instagram is such a popular source of publishing amongst teenagers, there is a large amount of alcohol related content for researchers to tap into.  It also provides an often more honest insight into behavior than provided by surveys.

Whilst users aren’t identifiable by age via their profiles on Instagram, the researchers developed effective techniques for filtering out users purely from their photos.

Photos were analyzed according to the tags attached to each image.  The researchers were looking for words associated with alcohol, including brand names and slang terms.

Not surprisingly, it emerged that young people were drinking more on weekends, but there were some distinctions with the brands drunk.

“There are several ways we can go about doing that,” the researchers say. “We can keep government agencies or schools better informed and help them design interventions. We could also use social media to incorporate targeted intervention and to measure the effect of any intervention. And perhaps other things we haven’t thought about.”

Double edged sword

Of course, whilst policy makers and health officials can use this kind of approach to better target health messages to underage drinkers, it could also be used by brands for the same purpose.

The researchers plan to check their initial results against traditionally acquired data to see just how robust their findings are, before then hopefully expanding their sample size considerably.  There is also a hope that the approach could work for other youth related problems, including smoking, depression and teenage pregnancy.

“This new method could be a useful complement to more traditional methods of measuring youth drinking,” said Elizabeth Handley, clinical psychologist and research associate at the University’s Mount Hope Family Center. “It could provide important new insights into the contexts of youth drinking and be a valuable tool for evaluating the effectiveness of school or community-based preventive interventions.”

In an age when our social and mobile data is ever more revealing about our habits and behaviors, it’s nice to see the data being put to positive use.