TheJakartaPost
Please Update your browser
Your browser is out of date, and may not be compatible with our website. A list of the most popular web browsers can be found below.
Just click on the icons to get to the download page.
Harvard research lets Instagram detect signs of depression
Change text size
Gift Premium Articles
to Anyone
Share the best of The Jakarta Post with friends, family, or colleagues. As a subscriber, you can gift 3 to 5 articles each month that anyone can read—no subscription needed!
Major depression is considered to be a leading cause of suicide throughout the world. (Shutterstock/-)
“A picture is worth a thousand words,” the old adage goes. Now it may also bare signs of clinical depression for Instagram users.
A research paper by Harvard researchers sampled 43,950 photos from 166 Instagram users using machine learning tools. They made use of algorithmic face detection, metadata components and color analysis to identify the signs of depression, reports Engadget.
(Read also: Eating alone increases chance of depression: Research)
Their study found that individuals who were more likely to suffer from depression had bluer, darker and grayer photos posted on their Instagram account. On the other hand, ratings that relied on photo attributes such as sadness, joy, etc., were weaker in predicting signs of depression.
In a sense, people who are “feeling blue” would tend to gravitate more to filters with shades of blue while those with a more upbeat disposition preferred warmer filters like Rise, Valencia and Earlybird. The study can be found here for more details.
