Your Instagram habits reveal more than just your favorite brunch spots. According to new research reported by NPR, users experiencing depression are more likely to filter their photos in black and white.
For their study, which was posted to arXiv.org earlier this month [PDF], researchers from Harvard University and the University of Vermont analyzed 43,950 photos from 166 Instagram accounts. Participants were asked to state whether or not they were diagnosed with clinical depression before the study. After breaking down photos by the number of faces, filters, color and brightness, and the amount of comments and likes, researchers found that certain trends could be traced back to people with depression.
While subjects with the condition were less likely to use any filter to begin with, one was particularly popular when they did. The study showed that Inkwell, which makes a photo black and white, was disproportionately preferred by depressed participants. Healthy participants, on the other hand, favored the Valencia filter which makes photos lighter.
The data also revealed that photos with faces were posted more frequently by depressed users, but with fewer faces per photo. And even though Instagram pictures from users with depression garnered more comments, they tended to receive fewer likes.
Using this information, researchers plugged Instagram photos into a computer algorithm to see how good it was at spotting depression. When given data from 100 users, it correctly identified individuals with the mental illness 70 percent of the time.
The study has yet to be peer-reviewed, and while Instagram filters may seem like an odd tool for making medical diagnoses, the authors point out that it may not be any worse than our current methods. They write:
“Our model showed considerable improvement over the ability of unassisted general practitioners to correctly diagnose depression. On average, more than half of general practitioners’ depression diagnoses were false positives[…]Given that mental health services are unavailable or underfunded in many countries, this computational approach, requiring only patients’ digital consent to share their social media histories, may open avenues to care which are currently difficult or impossible to provide.”
Instagram is just one tech habit that could potentially be used to diagnose mental illness. A study published in 2015 found that frequent phone usage may also be an indicator of depression.
Know of something you think we should cover? Email us at tips@mentalfloss.com.