Your Instagram Posts Can Reveal Your Mental Health Status

A new research revealed that your mental health status can be reflected on the kind of photos you choose to post on social media. Researchers involved in the study have trained a machine to detect people with depression on Instagram.

Did you know that your Instagram can tell a lot about you? Researchers Andrew Reece at Harvard University in Cambridge, Massachusetts, and Chris Danforth at the University of Vermont in Burlington found a significant connection between the colors in photos posted on Instagram and an individual's mental health status. The connection was so strong that the pair claimed it could be used to detect early signs of mental illness.

According to mirror.co.uk, researchers gathered data from 166 Instagrammers and analyzed 43,000 photos. They were then able to create a model using machine learning tools that can spot signs of depression. The model was able to accurately detect which Instagram user showed signs of depression just by using "color analysis, metadata components and algorithmic face detection." And about 70 percent of the time, the model accurately predicted the Instagram user that exhibited signs of depression even before they were first diagnosed.

Technologyreview.com reported that the researchers started by sourcing about 500 workers from Amazon's Mechanical Turk service who had Instagram accounts. These Turkers were asked by the researchers to complete a series of questionnaires which included a standard clinical depression survey. After that, Turkers were asked to share their Instagram posts for the study.

Among the 170 Turkers who agreed, about 70 of them were clinically depressed. The survey asked various additional questions about their condition, such as the original date of their diagnosis. The Instagram downloads resulted in a database of more than 40,000 pictures which the team then started to evaluate for the second time around, using crowdsourcing with a different group of Turkers. The researchers chose 100 most recent pictures to rate for each healthy user, and another 100 photographs for depressed individuals before their diagnosis.

Researchers found that depressed users most likely shared darker, bluer and more faded photos on their feeds. Also, the more comments a post received increased that likelihood of having been posted by a depressed person, but people with depression usually receive fewer "likes" for their photos. Ibtimes.co.uk also reported that even though depressed people may include faces in the pictures they post, researchers were able to find fewer faces per photo and included "more self-focused language".  They also noticed that these users tend to use more filters in their pictures.

It was also revealed that users usually choose Inkwell filter, which changes colored images into black-and-white. However, healthy participants were more into the brighter Valencia filter which lightens the tints of the images. However, the researchers pointed out that although their findings "suggest new avenues for early screening and detection of mental illness" they should not be taken as "enduring facts".

"Using only photographic details, such as color and brightness, our statistical model was able to predict which study participant suffered from depression, and performed better than the rate at which unassisted general practitioners typically perform during in-patient assessments," the study reads. It was also found that more than half of the general practitioners' depression diagnoses, on average, were false positives, the study said.