The colors in the photographs we post on Instagram may be indicative of what mood we’re in, according to a new study.
Researchers from the University of Vermont and Harvard developed a computer algorithm that was able to identify individuals with signs of depression by the types of images they share on social media. The photographic analysis in the study was more effective than most general practice doctors in diagnosing depression.
According to the study, Instagram feeds that are predominantly blue and gray and have fewer faces may belong to someone who is experiencing depression or another form of mental illness.
“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 study’s authors wrote.
The study included 43,950 photos from 166 people, half of whom reported being clinically depressed in the last three years. The algorithm was able to detect 70 percent of those with depression — as compared to a general practitioner’s average rate of 42 percent — by looking for images that were drained of color or had blue tones.
So while those diagnosed with depression may opt for Instagram filters like Inkwell, which drains the photo to a stark black-and-white, those in healthier spirits may prefer brighter, warmer filters like Valencia, according to the study.
The researchers also looked at the number of faces in photos, and found an interesting paradox: Depressed people were more likely to post photos with people’s faces in them, but those photos had fewer faces.
“Fewer faces may be an oblique indicator that depressed users interact in smaller settings,” the authors wrote. That could support — although the authors emphasize this is untested — a “sad-selfie hypothesis,” in that depressed people may post more photos of only themselves.