Depression and post-traumatic stress disorder are quiet killers; victims don’t always seek help, and friends may not feel empowered to intervene. That’s why there’s significant potential in the revelation, at a conference of statisticians earlier this month in Boston, that social media posts can provide strong evidence of depression and PTSD.
Currently researchers are mining social media for clues about mental illness, using only posts that users have agreed to make public. There’s certainly a hint of Big Brother in the mere notion of researchers plumbing through people’s postings to diagnose depression or trauma based on a particularly emotional tweet. And both the researchers and social media sites should guard against any possibility that the information would ever be used that way. But if scientists are able to perfect an algorithm that helps friends and relatives identify potentially depressed or traumatized individuals, the benefits could outweigh any sense of intrusion.
Social scientists are particularly intrigued by Twitter, with about 270 million active monthly users around the world and its potential to serve as, in the words of one scientist, “the largest observational study of human behavior we’ve ever known.”
At the Boston conference, US researchers presented preliminary findings on a study that was able to correlate significant traces of depression to tweets from areas of high unemployment. They also showed traces of PTSD in Twitter users’ posts from regions with high populations of veterans. Earlier this year, a team at Microsoft Research created an algorithm that scans tweets to predict depression and is accurate 70 percent of the time.
Twitter is, apparently, the quiet therapist to whom we reveal much more that we realize. As such, it could be a valuable public-health tool. More work needs to be done in considering how such information could be used while still preserving privacy, but it’s an inquiry worth pursuing.