What Do the Colors in the Images You Post Say About Your Mental Health?

The pictures you're posting on social media say more about you than you think.

By Elizabeth Yuko, Ph.D.
March 16, 2020

When we talk about social media and mental health, it’s usually in the context of how platforms like Twitter, Instagram, and Facebook can make us feel worse than we already do. But a new study out of the University of Pennsylvania School of Medicine took a look at a different aspect of this relationship: what the colors in the images people post on social media tell us about their mental health.

This research, which will be presented at the International AAAI Conference on Web and Social Media in Munich this June, found that Twitter users with anxiety and depression tended to post photos with lower aesthetic values, dull colors, or in grayscale. The aim of the study was to find out if artificial intelligence (A.I.) could pinpoint aspects of people’s profile photos that could help determine the state of a person’s mental health. 

Previous research from the University of Pennsylvania published in the Proceedings of the National Academy of Sciences in 2018 found that depression could be predicted as early as three months before an official diagnosis using A.I. to identify certain linguistic red flags in social media posts. But now that social media is more focused on images — thanks in part to the popularity of Instagram — the researchers wanted to see if pictures could also be used to detect mental illness.

“While the association between depression and language-use patterns is well-studied, the visual aspects of depression has not been,” the study’s lead author, Sharath Guntuku, Ph.D., a research scientist with Penn Medicine Center for Digital Health, said in a statement. “It is challenging to transform pixels that form the images to interpretable features, but with the advances in computer vision algorithms, we are now attempting to uncover another dimension of the condition as it manifests online.”

The researchers hope that their findings could help with the development of more accurate screening processes for depression and anxiety. “This tool is far from perfect to be used as a diagnostic tool. However, an automated machine learning tool could be a low-cost method for clinicians, with permission from their patients, to monitor their accounts and potentially detect elevated depression or anxiety levels,” Guntuku explained. “The clinicians could then refer patients who were flagged by the tool for more formal screening methods.”

About the writer:

Dr. Elizabeth Yuko is a bioethicist and writer as well as an adjunct professor of ethics at Fordham University. She has written for print and online publications, including The New York TimesThe Washington PostThe AtlanticRolling StoneCNNFodor’sLifehackerReader’s Digest and Playboy.

Outlier Disclaimer

This site is for educational purposes and not a substitute for professional medical care by a doctor or otherwise qualified medical professional. The information provided by Outlier Magazine is on the understanding that it does not constitute medical or other professional advice or services.

Copy link
Powered by Social Snap