The study revealed those who used “drink” and “bottle” had an increased risk of alcohol abuse. Those who used religious language, such as “God” and “pray,” were 15 times more likely to have diabetes. And terms expressing hostility, like expletives, were more predictive of drug abuse and psychoses.
"Our digital language captures powerful aspects of our lives that are likely quite different from what is captured through traditional medical data," senior author Andrew Schwartz said in a statement. "Many studies have now shown a link between language patterns and specific disease, such as language predictive of depression or language that gives insights into whether someone is living with cancer. However, by looking across many medical conditions, we get a view of how conditions relate to each other, which can enable new applications of AI for medicine."
The scientists now plan to investigate whether managing this data is feasible by asking patients to share their social media content directly to their doctors.
“This work is early, but our hope is that the insights gleaned from these posts could be used to better inform patients and providers about their health,” lead author Raina Merchant added. “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.”
» RELATED: Study: The more you use Facebook, the worse you feel