Your Instagram feed may be better at recognizing signs of depression than your doctor, according to a study from researchers at Harvard University and the University of Vermont.
According to a new report from Fast Company, researchers used a machine learning computer program to analyze 43,950 Instagram photos from 166 participants. They found that the computer’s analysis of Instagram feeds was better at diagnosing depression than a general practitioner.
Scientists from Harvard and Vermont universities created a computer program to recognize people with depression by studying the frequency at which they post and the types of images they share. By analyzing the Instagram behavior of people with mental health issues, they identified how people with depression use the app differently.
The study, published in the journal EPJ Data Science, found that users with depression posted more frequently than those without mental health issues and were more inclined to share photos that contained faces (albeit with a lower average face count per photograph than those without depression), but less likely to use filters.
“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,” the study reads.
The researchers found that healthy individuals chose Instagram filters like “Valencia,” which gave their photos a warmer brighter tone. Depressed people, however, were much more likely to use filters like “Inkwell,” which makes the photo black-and-white.
The researchers concluded that their findings support the idea that changes in mental health can be observed through social media. Provided efforts are made to ensure the data is held and analyzed in an ethical way, they argue that Instagram can be the basis of an effective tool for mental health screening.