Here's how your Instagram can help diagnose your depression

  • Here's how your Instagram can help diagnose your depression

Here's how your Instagram can help diagnose your depression

The AI system also looks at comments and "likes" received and uses a face recognition algorithm to automatically identify people in each photo.

Their reasoning? A computer might better be able to diagnose someone with depression than a doctor, since Global Positioning System only correctly identify depression in 42 per cent of cases (though it must be noted, that particular stat came from doctors who didn't use standard tools to arrive at their diagnoses). They also had the tendency to express photos in a color scheme of "bluer, grayer, and darker", the researchers revealed.

Markers of depression analysed included how frequently you post (depressed people post more), and how many different faces crop up in your images (depressed people have a lower average face count per photo).

While your social media feed may be one lens into your mental health, the study did find that general practitioners performed better than the computer program at ruling out depression.

A total of 43,950 photos were collected from 166 participants, around half of whom reported suffering from clinical depression in the last three years.

Instagram users in the study who had no depression diagnoses, on the other hand, favored filters such as "Valencia" that lightened the photos. The analysis showed a greater success rate for depression diagnosis.

Depressed people more frequently used blue, grey, and dark tones, and generally avoided filters, but when they did use them, they predominantly preferred the black-and-white Inkwell option. Reece and Danforth found that people who are depressed tend to view the world as gray or lacking in color.

"This study is not yet a diagnostic test, not by a long shot", said Danforth, "but it is a proof of concept of a new way to help people", Danforth added. The team wound up collecting nearly 44,000 photos from these volunteers, as well as responses to individual questionnaires assessing their level of depression.

This information was then used to see if the programme could predict who would go on to be diagnosed with depression by only looking at photos that were posted before their diagnosis.

The researchers were eventually able to create an algorithm that could determine whether or not an Instagram user would have depression.

More than 500 participants initially were recruited for the study, the researchers noted, but many dropped out because they would not consent to sharing their social media data.

Depression also made people less likely to use filters in their posts.

Danforth points out that while their research holds promise, the technology is still far from flawless. Even so, the possibility that social media analytics may offer a means of getting help faster to people in need is important, and should be explored further.