Roughly 95 million photographs are shared to Instagram every day, with more than 40 billion photos shared on the platform. With more than 600 million Instagram accounts open today, the social media photo-sharing platform is fast becoming one of the largest and extremely popular with fitness enthusiasts and professionals.
What if these photographs could help detect the early stages of depression? According to a study on how Instagram photos reveal predictive markers of depression, that may be possible. A team of researchers collected Instagram data from 166 individuals and used machine learning tools to identify markers of depression among those users. The researchers analyzed statistical features from close to 44,000 photographs on Instagram, using algorithmic face detection, color analysis, and metadata components.
The researchers evaluated other things, such as: “Are there people present? Is the setting in nature or indoors? Is it night or day? Did the photo receive any comments? How many ‘Likes’ did it get?” Even metrics like usage and posting frequency were analyzed to gauge the user’s mental state.
What they found was fascinating. According to previous research, “In studies associating mood, color, and mental health, healthy individuals identified darker, grayer colors with negative mood, and generally preferred brighter, more vivid colors. By contrast, depressed individuals were found to prefer darker, grayer colors.”
This new study found that “photos posted by depressed individuals tended to be bluer, darker, and grayer.” A higher number of comments also indicated depression on the part of the poster, but a higher number of “Likes” indicated the opposite. More frequent posts also meant a higher depression risk. Depressed users were more likely to post pictures with their faces, but had fewer faces (meaning fewer people) in each photo.
Depressed users also tended to use Instagram filters less. When they used filters, they tended to use the ones that converted color photographs to black and white. On the flip side, healthy participants used filters that lightened their photos’ tint. Of the pictures posted, those suffering from depression tended to be sadder.
What does this study prove? According to the researchers, “Health care providers may be able to improve quality of care and better identify individuals in need of treatment based on simple, low-cost methods.” They went on to say that being able to access this sort of content “may open avenues to care which are currently difficult or impossible to provide.”