KUALA LUMPUR, June 26 — Facebook posts alone can predict 21 medical conditions, including diabetes, depression, and anxiety, a study showed.
Futurity reported that the study published in PLOS ONE — which looked at the statistical association of language patterns (words and phrases) with medical conditions across 21 standard categories — found that Facebook posts alone predicted all 21 conditions.
For 10 of the diseases, Facebook reportedly predicted them better than demographic information like age and sex.
“Our predictions from language captures diagnosis of diabetes about as well as predictions based on one’s body mass index,” senior author H. Andrew Schwartz, assistant professor of computer science in the Stony Brook University College of Engineering and Applied Sciences from the US, was quoted saying.
“We can treat language pattern analogous to a genome and see similar diseases seem to have similar linguistic patterns.”
The research reportedly found strong correlations between Facebook posts and predicting mental illnesses like anxiety, depression, and psychosis in some patients. For diseases like diabetes and mental conditions, Facebook posts could predict illness more frequently than demographic information.
The words “drink” and “bottle” in Facebook posts, for example, could predict alcohol abuse better than demographic data.
People who most frequently used religious language on Facebook like “God” or “pray” were 15 times more likely to have diabetes than those who used these words the least.
Hostile language, including expletives and words like “dumb”, on the social media site indicated drug abuse and psychoses.
“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 Raina Merchant, director of Penn Medicine’s Center for Digital Health and an associate professor of emergency medicine, was quoted saying.
The research studied 20 million words in Facebook posts written by 999 consenting patients.