Twitter users send about 500 million tweets each day–an endless pool of data pouring into cyberspace. Now, the public health and epidemiology community is taking note of this pool of self-generated data and using it as a way to possibly address the origin and spread of disease.
One of Twitter’s biggest advantages? Speed. Traditional methods of gathering health information have a lag because researchers must wait for data from hospitals or other sources that are attributable to consumers taking action such as drug purchases. But, what about all of those that do not seek professional help for their ailment? How are we to track those sicknesses? And how can we get this information faster? Thanks to Twitter, now we can. Information gathered on Twitter is available in real-time and tagged with a location. So, Twitter has the ability to know when someone wakes up with, for example, a stomach ache in Long Island, NY because they have often put that information into cyberspace.
If this information can be properly harnessed, it could help keep hospitals and clinics from getting overwhelmed in the middle of an outbreak. Hospitals could be alerted that a disease is spiking in a certain area and stock up with medications and extra staff. According to The Washington Post, location-specific data can also identify clumps of noncommunicable diseases, allowing health officials to focus education efforts in the areas that need it most. In addition, Twitter can be an especially powerful tool in areas that currently have poor public health monitoring resources.
Many researchers have been hesitant to embrace Twitter data, claiming that it is too messy, cluttered and uncontrolled compared to more traditional public health research methods. Some contend, however, that they very messiness is Twitter’s biggest advantage: people tweet everything.
“It’s like a pulse on the world, because people will just tweet whatever, whenever,” says Christophe Girraud-Carrier, an associate professor of computer science at Brigham Young University, who studies what he and his colleagues have called “computational health science.” “Poll answers are filtered by perception or memory; on Twitter, we’re actually observing real behavior” as it happens.
So, what do you think about the idea of using Twitter data to gather public health information: is this concept a public health gold mine or a ticking time bomb?