Depression Symptoms: Instagram Algorithm Could Detect Disorder Better Than Your Doctor

  • Depression Symptoms: Instagram Algorithm Could Detect Disorder Better Than Your Doctor

Depression Symptoms: Instagram Algorithm Could Detect Disorder Better Than Your Doctor

In the study, 166 participants were recruited from the Amazon's Mechanical Turk and were asked to share their history of mental health as well as Instagram feed.

While seriously intuitive artificial intelligence may have a place in the medical future, for now it's still best to seek a trained medical professional to talk things through. "Our goal was to successfully identify and predict markers of depression in Instagram users' posted photographs", the researchers stated.

The researchers are hoping the new technique can be applied to people for early screening and detection of mental illness. The volunteers provided the researchers with information about past diagnoses of depression and responded to a questionnaire created to assess a person's level of depression.

One average the depressed participants posted photos that were more frequently dark, and more blue and gray than their control counterpart participants.

They analysed around 44,000 photos and used findings from well-established psychology research to look for clues in Instagram images that could reveal the user's state of mind. The black-and-white Inkwell was the most popular filter, although, depressed 'grammers were found to be less likely to use a filter at all.

Indeed, some of the photo features that the researchers identified "match common perceptions regarding the effects of depression on behavior", the authors noted.

The pics will tend to be darker, greyer and, well, "bluer", according to scientists.

The difference between photo filters healthy participants used in the study and what people with depression typically chose.

The report said they achieved the high success rate even when restricting themselves to posts made before the depressed individuals were first diagnosed.

"General practitioners were able to correctly rule out depression in non-depressed patients 81 per cent of the time, but only diagnosed depressed patients correctly 42 per cent of the time", the study reads. They rated 20 random photos chosen from the almost 44,000 included in the study. At least three different people rated each photo.

Although the team were also quick to say that the study only provides a limited diagnosis of depression, classifying it as a single-faceted condition, without consideration of other health conditions that may be present too.

They found those photos were often darker, bluer and grayer.

But the machine-learning algorithm did a better job, according to the study.

Chris Danforth, who is also a co-director of the university's Computational Story Lab, commented that it is obvious for a person to have knowledge on a friend than computer; however, while flipping through the images, he might not be able to identify depression that efficiently.