Your Instagram pictures tell the world a lot more about yourself than you realize. A new algorithm from researchers at Harvard and the University of Vermont have found an algorithm that reveals a lot about people on the social network.
You can tell a lot about someone based on their Instagram pictures — including whether or not that person is depressed, according to a new study from researchers at Harvard University and the University of Vermont. The study found that people who posted greyer or darker colored pictures on Instagram had a higher likelihood of depression.
The researchers were able to create an algorithm that examined photos on Instagram and then determined whether or not they had depression or any other mental illness. They found a connection between what types of colors people tend to use and their overall mental state, according to the study.
Scientists think that those who tend to post pictures that are greyer or darker on Instagram tend to be more depressed than those who post more colorful pictures, based on the results from 166 workers from Amazon’s Mechanical Turk service. The participants completed the questionnaire, and also shared pictures from their Instagram accounts.
Researchers selected 100 images from each participant. Then they asked people to rate them on a scale of 0 to 5 based on how interested, sad, or happy each photo looked to them. They then categorized the photos based on colors, saturation and even the number of faces in each shot. They found that decreased saturation and brightness and increased hue had the strongest correlation with depression.
“Using Instagram data from 166 individuals, we applied machine learning tools to successfully identify markers of depression,” the abstract states. “Statistical features were computationally extracted from 43,950 participant Instagram photos, using color analysis, metadata components, and algorithmic face detection. Resulting models outperformed general practitioners’ average diagnostic success rate for depression. These results held even when the analysis was restricted to posts made before depressed individuals were first diagnosed. Photos posted by depressed individuals were more likely to be bluer, grayer, and darker. Human ratings of photo attributes (happy, sad, etc.) were weaker predictors of depression, and were uncorrelated with computationallygenerated features.”