A new study has shown that Instagram photos can contain visual signs of depression.
According to lead researcher Andrew Reece, a graduate student with the Harvard University psychology department, the study’s computer software designed to scan photos for these clues accurately diagnosed people with depression seven out of 10 times.
“Depressed individuals in our study posted photos that were bluer, darker and grayer, compared to the posts of healthy participants,” Reece stated.
“Depressed people also tended to prefer Instagram’s Inkwell filter, which turns a color image into black-and-white,” he continued, “whereas healthy participants preferred the Valencia filter, which gives photos a warmer, brighter tone.”
To conduct the study, Reese and his co-author Chris Danforth, a professor at the University of Vermont College of Engineering and Mathematical Sciences, asked 1,666 people to share their Instagram feed and fill out a questionnaire regarding their mental health history. After collecting the questionnaire responses and almost 44,000 photos, the researchers evaluated the photos using software programmed to look for visual signs of depression.
“We were looking for subtle patterns associated with depression, and that required sifting through a lot of data to be confident about what we were seeing,” Reece stated. “Humans just aren’t very good at keeping track of information over many thousands of data points, so a computational approach was really the only feasible option for scalable and efficient analysis.”
With this, the researchers concluded that people with depression were more likely to choose a filter that drained the color out of images. Depressed persons also tended to post images that contained fewer faces, possibly because they were not as likely to engage in much social interaction.
The computer program’s depression detection rate may be more reliable than that of primary care doctors, who have shown to correctly diagnose depression in patients only about 42 percent of the time.
“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,” added Reece.
Some of the information revealed through the study, however, was not new. Prior research has established that people with depression tend to prefer darker or pale colors.
“There are reasons why depression is called blue, and why people associate red with raging, and why people say depression is like a dark or black cloud,” stated Dr. Igor Galynker, associate chairman for research at Mount Sinai Beth Israel’s psychiatry department in New York City. “Patients with depression choose to wear darker colors. They generally avoid bright stimulation altogether.”
While Reece and his fellow researchers hope that their software program will help to benefit doctors and patients with depression, they acknowledge that the program still has areas that need improvement.
“This is preliminary work, and it needs to be more thoroughly tested, vetted and replicated before we can safely claim that an algorithm can truly identify markers of depression in Instagram posts,” Reece said.
Nonetheless, the researchers’ ultimate goal is to use this line of research in suicide prevention.
“It is nearly impossible to predict suicide,” Galynker said. “If machine learning could predict who is potentially suicidal — based on what they say, what colors they use — that would be incredibly important.”
Featured image via Pixels