The photos we post to social media reveal more about our mental health than we realize, say researchers say in a new study. In fact, our Instagram posts may be better able to diagnose depression than even doctors.
The researchers found that when we’re blue, our photos become bluer too. They also get less colourful and darker, and the number of faces in our shots drops off too.
For the study, Chris Danforth, a professor at the University of Vermont’s Department of Mathematics & Statistics, and Andrew Reece of Harvard University, asked 166 volunteers to share their Instagram feeds, along with details about their mental health history.
The volunteers were chosen so that half had been clinically diagnosed with depression sometime in the last three years.
The team then analyzed the volunteers’ Instagram photos using a statistical computer model, looking for several visual markers associated with depression.
For example, research has shown that people with depression tend to prefer bluer, greyer and darker colours and shading compared to those in good mental health, so the computer algorithm was programmed to look for that.
The team found that people with depression did indeed post photos that were, on average, bluer, darker, and grayer.
Depressed people were also less likely to use Instagram filters, and when they did, they tended to favour the Inkwell filter, which turns photos into black-and-whites.
“In other words, people suffering from depression were more likely to favor a filter that literally drained all the color out the images they wanted to share,” the scientists write on their blog.
The healthy volunteers, on the other hand, chose filters that gave their photos a warmer, sunnier tone, such as Valencia.
Another key finding was that the depressed volunteers were more likely to post photos with faces — but these photos had fewer faces on average than the healthy people’s Instagram feeds – a sign that perhaps depressed users interact with fewer people.
That matches the research that has linked depression to reduced social interaction. But it might also be a sign that depressed people take more “selfies,” though the authors admit this hypothesis of the “sad-selfie” remains “untested.”
The researchers say their computer analysis model was so effective, it could detect depression periods about 70 per cent of the time. That’s more reliable, they say, than the 42 per cent success rate of family doctors trying to spot depression in their patients.
The team’s results were published in the journal, EPJ Data Science.
The statistical model the researchers performed even better at than volunteers who were asked to try to spot the photos of those in poor mental health.
Danforth said in a statement that while we tend to know our friends better than a computer could, “you might not, as a person casually flipping through Instagram, be as good at detecting depression as you think.”
The researchers say the social media photo-analyzing algorithm they developed holds the promise of one day offering a low-cost screening tool for mental health services.
“This study is not yet a diagnostic test, not by a long shot,” Danforth said in a statement, “but it is a proof of concept of a new way to help people.”