Using Facebook to diagnosis depression

I came across this article in Medical News Today, which reviews a study done in the medical journal Proceedings of the National Academy of Sciences. To make a long story short, the study reviews Facebook data and medical records, analyzing information posted by the more than 100 people who had been diagnosed with depression.

While there is ample evidence that social media can be a cause of depression (I have written about the topic before), this is the first time that I have ever seen published information which notes that social media can be used as a diagnosis tool for depression. That has some pretty interesting implications.

First, the study itself. Here’s one of the most important parts:

The scientists fed the information into an algorithm. In total, Eichstaedt [author of teh study] and colleagues analyzed 524,292 Facebook status updates from both people who had a history of depression and from those who did not.

By modeling conversations on 200 topics, the researchers determined a range of so-called depression-associated language markers, which depicted emotional and cognitive cues, including “sadness, loneliness, hostility, rumination, and increased self-reference” — that is an increased use of first-person pronouns, such as “I” or “me.”

The researchers found that the linguistic markers could predict depression with “significant” accuracy up to 3 months before the person receives a formal diagnosis.

Here’s a look at what words can be used to predict depression (none of this will be a surprise):

F4.large

Also notable is that more self-referential language is found more often in people with depression. That’s not really a surprise, as depression and narcissism are often linked.

To be perfectly honest, none of the above should be very surprising. Extended use of terms that indicate pain, distress or rumination would obviously indicate someone who is in a crisis. What is interesting, however, is that you can actually use these terms on social media to predictably and reliably diagnosis depression. That, to me, is fascinating. It is yet another tool in the toolbox for diagnosis depression, and as numerous studies have shown, depression remains massively under diagnosed, with some estimates showing that up to 2/3 of all individuals with depression are undiagnosed.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s