Facebook posts might be able to predict whether users are suffering from depression, according to a new study in the Proceedings of the National Academy of Sciences.
Researchers found the words people use in their posts indicate whether they are in need of mental health support for possible depression.
“We observed that users who ultimately had a diagnosis of depression used more first-person singular pronouns, suggesting a preoccupation with the self,” the team, led by Johannes Eichstaedt, wrote.
The study looked at 683 people who visited an emergency room and asked to see their Facebook pages. While the majority were not depressed, 114 had been diagnosed with depression based on their previous medical records.
The researchers examined each patient’s Facebook posts six months before their depression diagnosis to see if they contained hints about their mental state.
“Using only the language preceding their first documentation of a diagnosis of depression, we could identify depressed patients with fair accuracy,” they wrote in the study. Posts that used words such as "ugh, "miss," "hate," "pain," "miss," "cry" and "tears" were more commonly attributed to people later diagnosed with depression.
Since depression and suicide are both on the rise in the U.S., social media platforms might provide another outlet for researchers to obtain insight into mental health problems.
Facebook began its own program in 2015 that allowed users to flag accounts of people who had suicidal thoughts. The company has also used artificial intelligence algorithms to help prevent suicides, but it has come under scrutiny from experts for not going far enough.
Facebook did not immediately respond to Fox News for this story.
A different group of researchers reported in 2017 that Instagram may be able to determine whether people have depression based on the number of black-and-white or muted photos they choose to post.
Still, the findings raise important questions about people’s health privacy.
The researchers acknowledged that the application of an algorithm could change social media posts into protected health information.
“Similarly, those who interpret the data need to recognize that people may change what they write based on their perceptions of how that information might be observed and used,” they said.
For now, Facebook has made no mention of this tool being developed in the near future.
Fox News' Chris Ciaccia contributed to this report.