There are a lot of people who are addicted to social media platforms such as Facebook, Instagram, and Twitter. According to the scientists, an individual’s Facebook post can help in knowing the conditions related to health such as anxiety, depression, and psychosis. According to the researchers, the way of writing the post can help them to know about the symptoms just like they can know by examining the physical symptoms and all this by the patient’s consent.
The researchers from the University of Pennsylvania and Stony Brook University in the US used the automated data collection technique to study the FB posts of the 1,000 patients with their own consent and were asked to link their profiles to the electronic medical record data. Researchers made a different way to study the posts, first, by tracking the ways and language of the posts, second, by using the demographics in which they can identify the age and sex and some other necessities of the subject, and third, by combining both data together.
Researchers looked over 21 different conditions and it was found that all of the 21 conditions were already predictable and on the other hand, 10 of the conditions were better predicted by looking over the Facebook data, not the demographics. “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,” said Raina Merchant, an associate professor at the University of Pennsylvania. “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 said.
There were some results that were found predictable because of their Facebook data and not the demographics. For example, “drink” and “bottle” were shown to be more predictive of alcohol abuse. However, others were not as easy. Words like “dumb” were predicted as drug abuse or psychoses. “Our digital language captures powerful aspects of our lives that are likely quite different from what is captured through traditional medical data,” said Andrew Schwartz, an assistant professor at Stony Brook University.
“Many studies have now shown a link between language patterns and a specific disease, such as language predictive of depression or language that gives insights into whether someone is living with cancer,” said Schwartz. “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,” he said.