The team then analyzed the volunteers' Instagram photos using a statistical computer model, looking for several visual markers associated with depression. That's more reliable, they say, than the 42 per cent success rate of family doctors trying to spot depression in their patients.
The researchers do hope that the results help encourage scientists to conduct more research on the intersection of technology and depression signs, which could possibly lead to better early detection for mental illness in the future.
You might think that Instagram is just for heavily-filtered brunch snaps and smug selfies, but scientists have found that your grid reveals a lot more about you than what you got up to at the weekend. "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 examination". These and other recent findings (here, here, and here) indicate that social media data may be a valuable resource for developing efficient, low-cost, and accurate predictive mental health screening methods. By design, roughly half of our study participants reported having been clinically diagnosed with depression sometime in the last three years. Ideas from well-established psychology studies on color, brightness and shading preferences of people were used for analyzing the images.
As Instagram is used to share personal experiences, it is reasonable to infer that posted photos with people in them may capture aspects of a user's social life. They also tended to have more photos with a single person in them, while non-depressed people shared more group shots. Of those tones, the black and white Inkwell filter was more likely to be chosen, though depressed people on the whole were less likely to choose filters to begin with. Depressed people, for example, were more likely to post photos with darker, grey colors.
They added that the hypothesis of "sad-selfie" remains untested.
Researchers behind a new study published in EPJ Data Science designed a tool and created an algorithm that scanned through 43,950 images from 166 participants on Instagram (71 of whom were already diagnosed with depression), and flagged certain users as depressed.
They were able to up to a point, but not as effectively as the computer software.
Chris Danforth, who is also a co-director of the university's Computational Story Lab, commented that it is obvious for a person to have knowledge on a friend than computer; however, while flipping through the images, he might not be able to identify depression that efficiently. The volunteers provided the researchers with information about past diagnoses of depression and responded to a questionnaire created to assess a person's level of depression.