It may seem that everyone on Instagram is living their best life, but according to new research photos that are bluer, darker, and less populated might reveal a struggle with mental health.
Researchers from the University of Vermont and Harvard University, have found that they could diagnose depression by using machine learning to study the composition of Instagram photos.
According to the researchers, photos that are bluer, more gray, dark or with fewer faces indicate that the profile’s owner has depressive tendencies.
The computer’s detection rate of 70% is more reliable than the 42% success rate of general-practice doctors diagnosing depression in-person.
“This points toward a new method for early screening of depression and other emerging mental illnesses,” says Chris Danforth, a professor at the University of Vermont who co-led the new study. “This algorithm can sometimes detect depression before a clinical diagnosis is made.”
“So much is encoded in our digital footprint. Clever artificial intelligence will be able to find signals, especially for something like mental illness.”
To conduct the study, the researchers used the Instagram feeds of 166 people, around half of whom had reported having been clinically depressed in the last three years.
The researchers then collected and analysed 43,950 photos, using insights from well-established psychology research, about people’s preferences for brightness, colour, and shading. They also investigated the filters used by healthy and mentally ill people.
They found that healthy individual chose Instagram filters, like Valencia, that gave their photos a warmer brighter tone. Among depressed people the most popular filter was Inkwell, making the photo black-and-white.
Faces in photos also turned out to provide signals about depression. 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.
“People suffering from depression were more likely to favour a filter that literally drained all the colour out the images they wanted to share,” said Danforth and Andrew Reece of Harvard University who co-wrote the study.
“Fewer faces may be an oblique indicator that depressed users interact in smaller settings.”
More than half of a general practitioners’ depression diagnoses are false, but the computational algorithm was able to achieve a detection rate of 70%, while GPs are said to have only a 42% success rate.
The new study also shows that the computer model was able to detect signs of depression before a person’s date of diagnosis. “This could help you get to a doctor sooner,” Danforth says. “Or, imagine that you can go to doctor and push a button to let an algorithm read your social media history as part of the exam.”