--- title: "AI Can Tell if You’re Depressed by Reading Your Facebook Posts" description: "Researchers at the University of Pennsylvania found a way to predict if a person was going to be depressed by analyzing their Facebook data." date: "2018-10-17" modified: "2018-10-17" authors: - name: "Victor Tangermann" job_title: "Senior Editor" link: "https://futurism.com/authors/victor" url: "https://futurism.com/the-byte/ai-depressed-facebook-posts" categories: - "Artificial Intelligence" tags: - "facebook" - "mental health" - "the digest" - "university of pennsylvania" --- # AI Can Tell if You’re Depressed by Reading Your Facebook Posts ![Researchers at the University of Pennsylvania found a way to predict if a person was going to be depressed by analyzing their Facebook data.]() *\Image: Emily Cho\* ## Dr. Facebook It shouldn't come as much of a surprise, but Facebook knows a lot about you. And while the information it collects about you [isn't exactly in the safest of hands](), it *could* give mental health care professionals a huge leg up in predicting your future mental well-being — if you're willing to hand over your login information. In research [published this week]() *Proceedings of the National Academy of Sciences,* scientists at the University of Pennsylvania described how they were able to determine whether a particular Facebook user is likely to become depressed in the future, simply by analyzing their status updates. ## Robot Psychologists [*Wired* ]()[reports]() that the researchers used machine learning algorithms to analyze almost half a million Facebook posts — spanning a period of seven years — by 684 willing patients at a Philadelphia emergency ward. "We're increasingly understanding that what people do online is a form of behavior we can read with machine learning algorithms, the same way we can read any other kind of data in the world," UPenn psychologist Johannes Eichstaedt told the magazine. The algorithms looked for markers of depression in the patients' posts, and found that depressed individuals used more first-person language — a finding in line with many previous studies. The algorithm got so good at catching those markers that it could predict if a Facebook user was depressed up to three months prior to a formal diagnosis by a health care professional. ## The Human Touch For now, take these results with a grain of salt — this won't ever be a substitute for human psychologists, because there are far too many variables. But social media information — along with heart rates or sleep data collected by fitness trackers — could be a powerful tool to catch mental health problems early on. That is, if we're willing to share that kind of information with them in the first place. **Read More: [Your Facebook Posts Can Reveal If You're Depressed]() \[*Wired*\]** **More on mental health and social media: [Instagram is Trying to Make Users Feel Better Without Scaring Them Off]()** ## Author I've been at Futurism since 2017, where my role has evolved to encompass design, writing, and increasingly editing. I've always been fascinated by space exploration and advanced transportation, which I've leaned into by interviewing luminaries in those fields while closely following the dimensions of policy and regulation that allow next-generation projects to succeed -- or, sometimes, to fail. I'm also keenly interested in the effects of generative AI on society, policies, and democratic institutions, as well as clean energy, physics and biology, and the vagaries of tech leadership. My work for Futurism has been cited by publications including Ars Technica, Gizmodo, PC Magazine, Jalopnik, Fox News, and the New York Post. I spent my childhood living in locations including Manila, the Philippines, and Geneva, Switzerland, attended McGill University, and now live in Toronto, Canada. Before Futurism I worked at AskMen and a small photography studio. In my free time, I'm an avid gardener, foodie, and craft beer lover, as well as a maker of artisanal hot pepper sauces. I have a magnificent dog named Freida. ### Author social links [Bluesky]()