New York — Emergence of social media networks has made communication and the spread of opinions between millions of people around the globe much easier and more instantaneous than ever. Now, the world’s popular micro-blogging service Twitter has once again established itself to be more than a mere diversionary tool for gossiping around. The 140 character messaging service that has been attributed with doing just about everything, may even turn out to be a medical goldmine.
Keeping oneself healthy is everyones’ priority in life. And, to get a feel for what society’s health experts are discussing, you would probably talk to a doctor or log on to the health department’s website. But, thanks to the chirping bird, you could now just check Twitter as well.
However, a recent study shows that a couple of computer scientists at Johns Hopkins University in Baltimore have been mining more than two billion tweets related to health, and found that the popular micro-blogging website portrayed the ills that plague us and the treatments sought as a result, BBC News reported.
The research also showed that a lot of people are misguided about the right treatments for their ailments. Besides, this is also another example of the benefits of “big data” the capturing, storing and analyzing of massive data sets to uncover information and relationships.
Researchers, Mark Dredze and Michael J. Paul used specifically developed computer application to comb through 2 billion tweets posted between May 2009 and October 2010. And, from all that big-data noise, the scientists accumulated useful information and trends related to health matters, such as allergies, flu cases, insomnia, cancer, obesity, depression, and pain. They even discovered findings previously unknown to members of the medical community.
The initial challenge in the process was to develop filters capable of differentiating between tweets about actual health issues and tweets containing health-related words or phrases, such as “fever” (such as “zomg i’ve got bieber fever!!!”) or “gas” (e.g. “Gas prices are way too high!”). Hence, the researchers formulated a unique categorization and filtering system that programmed their computers to disregard the words and phrases used in the billions of Twitter posts that do not relate to health.
For example, “we found that some people tweeted that they were taking antibiotics for the flu,” Ph.D. student Michael J. Paul, one of the researchers for the project, told BBC News. “But antibiotics does not work on the flu, which is a virus, and this practice could contribute to the growing antibiotic resistance problems.”
Beyond various analysis, the discoveries also enabled us to establish when allergy and flu seasons had peaked in various parts of the country. “We were able to ascertain from the tweets that the allergy season started earlier in the warmer states and later in the Midwest and the Northeast,” Dredze said.
Although it can be a good research tool, both Dresze and Paul agree that there is a lack of consistency in users’ postings and limitations involved in social media research. However, users post haphazardly what they want, when they want, and because many posters only comment once or twice on their illness it becomes hard to track the extent and severity. Because social media use is dominated by a younger generation, opinions from many senior citizens were left out of the data.
“In our study,” Paul said, “we could only learn what people were willing to share. We think there is a limit to what people are willing to share on Twitter.”
Furthermore, the U.S. Library of Congress has already begun storing an archive of public tweets to be used for academic purposes and according to the John Hopkins study, “We could learn new symptoms or treatments, which may be of particular interest, such as if users have developed new home remedies.”
Nevertheless, through their investigation the researchers found surprising data that may be useful in future medical research. Keeping track of Twitter and other social networking data may be an effective way to gain insight on opinions of people on a more personal level.