Computer analysis of social media posts was more accurate than humans in identifying people in distress, said the U.S. scientists behind the study.
"When they did select a filter they were more likely to use the filter that converted color images to black and white".
More obviously, a so-called "sadness selfie" would highlight that someone was struggling.
Prof Danforth and United States colleague Andrew Reece from Harvard University wrote in a blog post accompanying the study: "Pixel analysis of the photos in our dataset revealed that depressed individuals in our sample tended to post photos that were, on average, bluer, darker, and greyer than those posted by healthy individuals".
In contrast, a British study found Global Positioning System pick up depression accurately in only 42 per cent of cases.
The scientists asked volunteers recruited from Amazon's Mechanical Turk crowd sourcing site to share both their Instagram feeds and mental health history.
The researchers found that depressed people were more likely than healthy people to post a photo with people's faces, but these photos had fewer faces on average than the healthy people's Instagram feeds.
Faces in photos also turned out to provide signals about depression.More news: J&K: Gun Battle Between Security Forces and Terrorists Underway in Pulwama's Drubgam
That's the conclusion of new research showing that computers, applying machine learning, can successfully detect depressed people from clues in their Instagram photos. The research team built a tool that analyzed the posts and identified depression through markers determined in previous research, such as the tendency of depressed people to prefer grayer, darker colors, and to show less evidence of social activity (which the researchers thought might be evidenced by the absence of faces in posted images). All-in-all, we collected 43,950 photos posted to Instagram for analysis. Among depressed people the most popular filter was Inkwell, making the photo black-and-white.
The computer program then scoured their images posted to the social media platform for details that have been previously linked to healthy and depressed individuals.
"Fewer faces may be an oblique indicator that depressed users interact in smaller settings", the authors wrote.
Scientists found that people with good mental health tended to favour bright Instagram filters such as Valencia. Yet, those volunteers were not able to complete the task as efficiently as the statistical computer model; the rating done by humans lacked much correlation with the features of the photos that were identified by the computer.
Chloe Grass-Orkin, from the charity Rethink Mental Illness, said the study offered could offer new prospects to identify people in need of support.
Study co-leader Professor Chris Danforth, from the University of Vermont, suggested that the analysis could help to identify people with depression earlier and with greater accuracy in future.
We were able to observe these differences reliably, even when only looking at depressed users' posts made prior to receiving a clinical diagnosis of depression.