Earlier this year it was reported that, despite its popularity, Instagram may be the worst social media platform for young women. That’s because it’s linked to a host of problems like negative body image and FOMO (aka, the fear of missing out), likely thanks to the social media site’s use of reality-distorting filters.
Now a new study finds these same filters may actually hold the key to understanding an individual’s mental health. That’s right: Your preference of Juno over Willow may be connected to how happy or sad you feel.
Scientists have derived an algorithm that can accurately diagnose depression 70 percent of the time just from looking at your selfies or photos of your avocado toast. What’s interesting is it doesn’t really matter what you post; rather it’s the Insta-filter you’re using to doctor up your photos that’s so revealing.
According to the algorithm, when you get the blues it shows up in your feed.
“Depressed individuals in our study posted photos that were bluer, darker and grayer as compared to the posts of healthy participants,” Harvard University graduate student and lead researcher Andrew Reece tells CBS News. He and co-author Chris Danforth, a professor at the University of Vermont College of Engineering and Mathematical Sciences, looked at the Instagram feeds of 166 people who were also asked to fill out questionnaires about their mental health. In total, 44,000 photos were analyzed using a unique software that could visually detect signs of depression.
The researchers found that the filter of choice for depressed ‘grammers was often Inkwell, which transforms a colorful snap into a black-and-white photo. “Healthy participants” opted for Valencia, a tone-brightening filter. In other words, depressed individuals seemed to want to drain all the color out of their photos, while happier people wanted to liven them up. “Our results suggest that depression quite literally makes people see their world through a darker, grayer lens,” Reece said.
Another not-so-surprising finding of the study? Depressed people post more single-person shots than group shots, which researchers believe could be because they aren’t as social.
Previous studies have found that physicians accurately diagnose depression only around 40 percent of the time, but Reece and Danforth maintain their computer program correctly detected it seven out of 10 times — which means this algorithm is 30 percent more effective in diagnosing the condition than a real, live human with a medical degree. Crazy, right?
But researchers aren’t suggesting you ditch your doctor and allow a computer to prescribe you medication. Instead they hope this new information will complement the diagnostic process. “It’s clear that depression isn’t easy to diagnose, and the computational approach we’ve taken here may end up assisting, rather than competing with, health care professionals as they seek to make accurate mental health assessments,” Reece says.
What Do YOU Think?
What is your favorite Instagram filter? Do you think it accurately describes your mental health as described in this study? Do you think computers will be more instrumental in diagnosing mental health conditions in the future? Let us know your thoughts in the comments.