Photo by Brian Solis | CC BY 2.0
Penn Medicine researchers have found that language in Facebook posts can help identify 21 medical conditions including diabetes, anxiety, and depression.
Published in the PLOS ONE journal on June 17, the study analyzed Facebook status updates with at least 500 words written by 999 consenting patients. From March 2009 to October 2015, researchers used nearly 950,000 posts to evaluate the language used in Facebook posts and the users’ demographics such as age and sex.
“Because such [social media] content is constantly being created outside the context of health care systems and clinical studies, it can reveal disease markers in patients’ daily lives that are otherwise invisible to clinicians and medical researchers,” the study read.
Researchers found that social media content could predict all 21 conditions considered in the study, according to The Atlanta Journal Constitution. Furthermore, 18 of the conditions were better predicted by considering both demographics and Facebook language rather than by demographics alone. Ten of the conditions were better predicted by Facebook language than demographic information, according to Science Daily.
Hostile language in posts such as “dumb” and swear words indicated drug abuse and psychoses, according to the study. The top 25% of patients using religious language such as “God” or “pray” were 15 times more likely than patients in the bottom 25% to have diabetes.
Lead researcher Raina M. Merchant is the Associate Vice President and an associate professor of Emergency Medicine at Penn Med. Merchant told Science Daily that later this year, she will ask patients to directly share their social media content with their doctors to investigate if managing and applying this data would be feasible.
"One challenge with this is that there is so much data and we, as providers, aren't trained to interpret it ourselves or make clinical decisions based on it," Merchant said to Science Daily. "To address this, we will explore how to condense and summarize social media data."
Merchant, however, said she remains hopeful the study's insights can be used to better inform patients and providers about their health.
“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," Merchant told The Atlanta Journal Constitution.
The Daily Pennsylvanian is an independent, student-run newspaper. Please consider making a donation to support the coverage that shapes the University. Your generosity ensures a future of strong journalism at Penn.
Donate