Facebook, Twitter content can show signs of a person's health condition: study

A new study published online in the journal BMJ Quality & Safety shows a relationship between language used in posting in social media and the user's everday life and health, EurekAlert reports.

This is a first of its kind, and researchers from the Perelman School of Medicine at the University of Pennsylvania found that adults who use Facebook and Twitter are willing to let a third party use their social media data and medical data for research purposes. Moreover, creating a language databank helps build a relationship between social media content and the user's health.

According to Raina M. Merchant, MD, MSHP, director of the Social Media and Health Innovation Lab and an assistant professor of Emergency Medicine at Penn Medicine, who is also the study's senior author, "We don't often think of our social media content as data, but the language we use and the information we post may offer valuable insights into the relationship between our everyday lives and our health."

Over the course of seven months, over 1,000 patients who visited the Emergency Department were asked by researchers if they used social media and if they were willing to share this data in order to build a research database. This research database composed of social media data, like other existing genomic data banks, enables researchers to determine relationships between the participants' social media content and their health. Researchers analyzed data dating 2009 onwards, and found that there were around 1.4 million posts and tweets to Facebook and Twitter, with almost 12 million words.

Results revealed that some posts are as specific as telling readers that the user forgot to take medication on a certain day, while others showed several posts of unhealthy food. Researchers also found that changes in word complexity may suggest cognitive decline, while the shift in number of words per post or network size may imply a depressed mental state. Posts also contained information on how the user adhered to prescribed medications, new medical conditions, and health behaviors relating to diet and exercise.

According to Newswise, Dr. Merchant believes that "The social media and health data bank, which we are continuing to build, serves a valuable purpose in helping us think about health in new ways, some of which we haven't even begun to consider. Just as genetic information is banked to track potential future health, previously unobservable social media postings—made up of words, language, and conversations—may also be banked from consenting individuals and evaluated for potential correlations with health and health outcomes."

Science Codex reports that according to Lyle Ungar, PhD, a professor of Computer Science at the University of Pennsylvania's School of Engineering and Applied Science, and a co-author on the study, the results show that social media is "a promising avenue for exploring how patients conceptualize and communicate about their specific health issues."