Facebook posts could help doctors spot alcoholism, diabetes or depression, study says

The research suggests they may be a more accurate predictor than demographics.

Shelby Brown Editor II
Shelby Brown (she/her/hers) is an editor for CNET's services team. She covers tips and tricks for apps, operating systems and devices, as well as mobile gaming and Apple Arcade news. Shelby also oversees Tech Tips coverage. Before joining CNET, she covered app news for Download.com and served as a freelancer for Louisville.com.
  • She received the Renau Writing Scholarship in 2016 from the University of Louisville's communication department.
Shelby Brown
2 min read

Is Facebook your new doctor?

NurPhoto/Getty Images

As time consuming as Facebook can be sometimes, a new study suggests what you post could offer a window into your health. The language used in Facebook posts could be helpful in predicting diseases and mental health disorders, according to research from Penn Medicine and Stony Brook University. The study, published Monday in the journal PLOS ONE, suggested that social media posts could be monitored like physical symptoms.

Researchers found that the use of the words "drink" and "bottle" were predictive of alcohol abuse. While that one might seem obvious, the study also found that people who most often mentioned "God" and "pray" were 15 times more likely to have diabetes than those who used them less. 

For some medical conditions, predictions based on Facebook posts were "significantly more accurate" than those from demographics alone, the study found. However, Facebook and demographic information combined were more accurate at predicting conditions than just social media posts alone.

"As social media posts are often about someone's lifestyle choices and experiences or how they're feeling, this information could provide additional information about disease management and exacerbation," lead author Dr. Raina Merchant, the director of Penn Medicine's Center for Digital Health and an associate professor of emergency medicine, told Science Daily. Merchant noted that the research is still early.

The researchers used an automated data collection technique and analyzed the entire Facebook post history of nearly 1,000 patients who agreed to have their electronic medical record data linked to their profiles. The study analyzed the Facebook post language and demographics separately, then combined the two data sets.

Merchant didn't immediately respond to a request for further comment.

Watch this: Facebook readies its own cryptocurrency, Google's Pixel 4 and Musk under fire (again)