Do you like to post black and white photos or add filters to make colors pop? Be that as it may, the photos you post on your Instagram account can provide clues about your mental health , according to a study carried out by researchers at the University of Vermont (USA).
Using machine learning, the artificial intelligence used in the study was able to detect which people had depression and which did not, based on their Instagram photos and with randomly selected volunteers.
“This points to a new method for the early detection of depression,” said Christopher Danforth, leader of the work.
For the study, researchers examined the Instagram photos of more than 160 volunteers, recruited from Amazon Mechanical Turk, an online crowdsourcing platform. Participants provided the experts with information about their past diagnosis of depression and responded to a questionnaire designed to assess a person’s current level of depression.
About half of the people in the study had been diagnosed with depression in the past three years.
When the researchers analyzed the nearly 44,000 images, they found that the messages from users with a probable diagnosis of depression were bluer, grayer, and darker than the images from users with no inclination toward depression.
The use of a photographic filter was less common among individuals diagnosed with depression than among those without. But when individuals diagnosed with depression used filters, many opted for black-and-white filters like “Inkwell .” In fact, some of the photographic characteristics the researchers identified “coincide with common perceptions regarding the effects of depression on behavior,” the authors noted. For example, previous studies have already suggested an association of depression with a preference for darker, bluer, and monochromatic colors.
People prone to depression were also more likely to post photos without people or with fewer people per photo , compared to other users.
Using the Instagram photos and the mental health story collected in the first part of the study, the researchers tested the depression-detecting algorithm at the same time with a different group of volunteers to see which of them, human or intelligence. artificial, was closer to the real result of the mental health of the participants.
The results revealed the machine learning algorithm did a better job than human peers, as the AI was able to correctly identify individuals with possible depression 70% of the time.
“Obviously, you know your friends better than a computer, but a person who happens to pass by Instagram is not that good at detecting depression,” Danforth said.
Despite the conclusions, the study has limitations. For example, experts claimed to have used a broad definition of depression, so examining specific types of depression could lead to different results than those obtained.
Also, much more research is needed before this type of technology can be used to diagnose mental health conditions. “ This study is not yet a diagnostic test, but it is a proof of concept for a new way to help people, ” concludes Danforth.
Referencia: Instagram photos reveal predictive markers of depression. 2017 EPJ Data Science. doi.org/10.1140/epjds/s13688-017-0110-z
