Social media is more than just social media. And researchers know exactly how to make more of it. This gigantic platform on the internet is a one-stop open information source about the lives of millions of people and it’s exactly what scientists could use, to say- track down the flu, or even worse, an epidemic.
A team lead by Alessandro Vespignani, Distinguished University Professor at Northeastern University, has developed a unique computational model to project the spread of the seasonal flu in real-time. It uses posts on social media platforms in combination with key parameters of each season’s epidemic, including the incubation period of the disease, the immunisation rate, how many people an individual with the virus can infect, and the viral strains present.
“In the past, we had no knowledge of initial conditions for the flu,” says Vespignani. To ascertain more information, the researchers incorporated Twitter into their parameter-driven model. Every tweet about someone feeling unwell, having a headache or maybe a cold was analysed. “We were not looking for the number of people who were sick because Twitter will not tell you that. Twitter, which includes GPS locations, and could reveal how much flu there is at a given location. By looking at how many people were tweeting about their symptoms or how miserable they were because of the flu, we were able to get a relative weight in each of those areas of the U.S.”
Over a period of time, Vespignani and his team used their algorithms week by week with the key parameters informed by the Twitter data. “This gave us a large number of possible ways the disease might evolve,” says Vespignani. This data is what the public health agencies and the epidemiologists really care about. It will enable public health agencies to plan ahead in allocating medical resources and launching campaigns that encourage individuals to take preventative measures such as vaccination and increased handwashing. “Our model is a work in progress,” emphasizes Vespignani, hopeful to improve their model by working on other digital sources, too, as well as online surveys.