A computer program trained to diagnose depression from the images was correct 70 per cent of the time, a study led by Harvard University and Dr Christopher Danforth, of Vermont University, found. People who aren't depressed, on the other hand, preferred the Valencia filter, which brightens the image.
The scientists say their new study also showed that the algorithm was able to detect signs of depression before a person's date of diagnosis.
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.
Depression is also characterized by reduced or avoidant social engagement.
The researchers then developed an algorithm that analyzed elements of the Instagram photos, including components like colors, the number of people in a picture and the number of comments and likes the photo received.
They found that posts of depressed people both before and after diagnosis tended to have more blue, dark, or gray tones than those of healthy people.
Depressed individuals in our sample tended to post photos that were, on average, bluer, darker, and grayer than those posted by healthy individuals.Researchers wanted to see what qualities depressed users' photos had in common. More news: Bayern Munich beats Borussia Dortmund to win 2017 Supercup
More news: High Court rejects bid to prosecute Tony Blair
More news: More Apple iPhone 8 insights, no presence of in-screen Touch ID
"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", Galynker said.
The study, published Tuesday in the journal EPJ Data Science, analyzed almost 44,000 Instagram photos from 166 volunteers, who also shared their mental health history.
"Obviously, you know your friends better than a computer, but you might not, as a person casually flipping through Instagram, be as good at detecting depression as you think", Danforth said.
Danforth points out that while their research holds promise, the technology is still far from ideal. Rather, it may help give an "early warning" of depression, Danforth told BuzzFeed News.
"We have a lot of thinking to do about the morality of machines", he said.
We do feel strongly that there's an important ethical discussion that must occur in step with these technological developments, regarding data privacy and the implications of applying sophisticated analytical tools in an online medium which doesn't forget.
Study co-leader Professor Chris Danforth, from the University of Vermont, US, said: 'This study is not yet a diagnostic test, not by a long shot, but it is a proof of concept of a new way to help people.