Your tweets could help track the spread of seasonal flu in real time, say scientists who have developed a new model that uses Twitter posts to predict how the infection may affect a population.
Researchers from Northeastern University in the US gathered tweets along with parameters of each season’s epidemic, such as the incubation period of the disease, the immunisation rate, how many people an individual with the virus can infect, and the viral strains present.
They applied forecasting and other algorithms to the key parameters informed by the Twitter data. Researchers then matched the resulting simulations with the surveillance data generated by the US Centre for Disease Control (CDC) and clinical and personal reports of influenza- like illnesses from the three countries.
They analysed the evolving dynamics revealed in the past data, and were able to select the model that would most likely forecast the future.
Researchers then tested the model against official influenza surveillance systems. They found that it accurately forecast the disease’s evolution up to six weeks in advance - significantly earlier than other models.
