Instagram may be more accurate at diagnosing depression than a doctor, study suggests

ai program uses instagram to diagnose depression 45606019  beautiful alone sensual girl on the beach
Aliaksei Lasevich / 123RF
A new artificial intelligence program can pick up on the early signs of depression before humans (and even humans who are general practitioners) can — and just by using Instagram. A team of researchers from Harvard and the University of Vermont recently developed a machine learning program that correctly identified which Instagram users were clinically depressed with 70 percent accuracy.

In a study published on Aug. 10 from Andrew G. Reece and Christopher M. Danforth, the group applied the machine learning platform to 166 Instagram profiles containing 43,950 photos. The system uses markers to detect if Instagramers are depressed, analyzing aspects like color, metadata, and face detection.

“Using only photographic details, such as color and brightness,” the study says, “our statistical model was able to predict which study participants suffered from depression, and performed better than the rate at which unassisted general practitioners typically perform during in-person patient assessment.” Based on 118 earlier studies, the researchers found that general practitioners only correctly diagnosed depression 42 percent of the time.

While other studies have shown how written information from social media can be used to predict psychiatric disorders, the group says that earlier research failed to incorporate visual posts.

Using earlier studies, the group taught the computer system to identify markers for depression. For example, since earlier research showed that depressed individuals preferred darker, grayer colors, the program analyzed color as one factor, including the role that Instagram’s filters play on those colors.

The program also considered factors like how often users post, since depression often correlates with reduced social activity. In addition, the system also counted the number of people in the image using face detection and also factored in the number of likes and comments each photo received.

Photos posted from depressed Instagramers were more likely to get comments, but less likely to receive likes. The study participants with a depression diagnosis were more likely to use no filters at all, and when they did, often favored the Inkwell filter. And while depressed individuals were more likely to show faces in their posts, they often had fewer faces in each image compared to other users.

To see how well the average person is able to pick up on signs of depression using only Instagram photos, the researchers also had a group of people rate each photograph. The participants didn’t know they were looking at Instagram photos, and didn’t know that the study was being conducted on depression. The researchers asked each person to rate the image from 1-5 in four categories: happy, sad, likability and interestingness.  The ratings for happy and sad tended to correspond with the images shot by individuals diagnosed with depression, while the other ratings, including “likability” and “interestingness,” did not.

The researchers also took the same machine learning program and applied it to only the posts that were dated before the individual was diagnosed. Using earlier photos, the programs was still able to accurately predict which users were depressed more than half the time.

While the findings look promising, the study’s authors also noted that the program has some shortcomings, saying that the information shouldn’t be taken as “enduring facts” but as a “methodological foundation upon which to build and refine subsequent models.” For starters, 43 percent of the initial participants refused to give their Instagram information, due to privacy concerns. Another issue is that social media trends will change over time, and such a machine learning program would need to be continually updated, the researchers said.

Emerging Tech

Awesome Tech You Can’t Buy Yet: camera with A.I. director, robot arm assistant

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Emerging Tech

Dinosaurs never stood a chance after asteroid impacts doubled 290M years ago

The number of asteroids pummeling Earth jumped dramatically around 290 million years ago. By looking at Moon craters, scientists discovered that d the number of asteroid impacts on both Earth and the Moon increased by two to three times.
Social Media

Spice up your Instagram videos by adding your top tunes to the soundtrack

Have you ever taken a beautiful video, only to have it ruined by some jerk in the background yelling curse words? Here's a list of apps you can use to add your own music to Instagram posts as well as your Story.
Health & Fitness

In search of the fountain of youth, beauty companies turn to tech

Beauty tech is a fairly new concept, but at CES 2019, companies such as Olay, L’Oreal, and Neutrogena were fully embracing it with all kinds of gadgets that promise to give you glowing skin.
Social Media

No yolk! A photo of an egg has become the most-liked post on Instagram

Until this weekend, the most-liked post on Instagram was of Kylie Jenner's baby daughter, which has around 18 million likes. It's now been knocked off the top spot not by a stunning sunset or even a cute cat, but by an egg.
Social Media

Invite your friends — Facebook Events can now be shared to Stories

Facebook is testing a way to make plans with friends to attend an event -- through Stories. By sharing an event in Facebook Stories, users can message other friends interested in the event to make plans to attend together.
Social Media

A quick swipe will soon let you keep bingeing YouTube on mobile devices

The YouTube mobile app has a new, faster way to browse: Swiping. Once the update rolls out, users can swipe to go to the next (or previous) video in the recommended list, even while viewing in full screen.
Photography

Starting your very own vlog? Here are the best cameras to buy

Any camera that shoots video can be used to vlog, but a few models stand out from the crowd thanks to superior image quality, ergonomics, and usability. When it comes to putting your life on YouTube, here are the best cameras for the job.
Social Media

Twitter extends its new timeline feature to Android users

Twitter users with an Android device can now quickly switch between an algorithm-generated timeline and one that shows the most recent tweets first. The new feature landed for iPhone users last month.
Social Media

YouTube to crack down on dangerous stunts like the ‘Bird Box’ challenge

YouTube already bans content showing dangerous activities, but new rules published by the site go into greater detail regarding potentially harmful challenges and pranks, including certain blindfold- or laundry detergent-based stunts.
Social Media

Nearly 75 percent of U.S. users don’t realize Facebook tracks their interests

Did you know Facebook tracks your interests, including political and multicultural affiliations? According to a recent Pew study, 74 percent of adult users in the U.S. have no idea Facebook keeps a running list of your interests.
Mobile

It’s back! Here’s how to switch to Twitter’s reverse chronological feed

Twitter has finally brought back the reverse chronological feed, allowing you to see your feed based on the newest tweets, rather than using Twitter's algorithm that shows what it thinks you want to see. It's easy to switch.
Social Media

Nearly a million Facebook users followed these fake Russian accounts

Facebook purged two separate groups behind more than 500 fake accounts with Russian ties. One group had ties to Russian news agency Sputnik, while the other had behavior similar to the Internet Research Agency's midterm actions.