Mark Dredze and Michael J. Paul fed 2 billion public tweets posted between May 2009 and October 2010 into computers, then used software to filter out the 1.5 million messages that referred to health matters. Identities of the tweeters were not collected by Dredze, a researcher at the university’s Human Language Technology Center of Excellence and an assistant research professor of computer science, and Paul, a doctoral student.
“Our goal was to find out whether Twitter posts could be a useful source of public health information,” Dredze said. “We determined that indeed they could. In some cases, we probably learned some things that even the tweeters’ doctors were not aware of, like which over-the-counter medicines the posters were using to treat their symptoms at home.”
By sorting these health-related tweets into electronic “piles,” Dredze and Paul uncovered intriguing patterns about allergies, flu, insomnia, cancer, obesity, depression, pain and other ailments. “There have been some narrow studies using Twitter posts, for example, to track the flu,” Dredze said. “But to our knowledge, no one has ever used tweets to look at as many health issues as we did.” –Source
I found this approach to public health quite intriguing. Certainly mining Twitter data for public health trends has some major limits, but I also think it could have some real benefits to understanding user actions and even trends happening across the country.
I think the best example I can think of was my approach to allergies. I have allergies, but they’re not terribly bad. However, my previous boss had allergies that were much worse. I didn’t personally want to be taking allergy meds around the clock. So, I just kept an eye on my boss. As soon as she started to get a reaction, I’d start taking my allergy meds. This method worked really great for me, until I quit that job.
What if I could apply this same principle to Twitter? I’d love to get an alert from some program that told me when people in Las Vegas were starting to complain about allergies. It would be essentially automating what I was doing naturally with my old boss. That’s a service I’d find very interesting and useful.