Communications of the ACM
Researchers Use Twitter to Track the Flu in Real Time
Northeastern University researchers have developed a computational model to project the spread of the seasonal flu in real time, using Twitter posts in combination with key parameters of each season's epidemic.
Credit: Greg Grinnell
Researchers at Northeastern University have developed a computational model to project the spread of the seasonal flu in real time.
The method uses Twitter posts in combination with key parameters of each season's epidemic, including the incubation period, the immunization rate, how many people an individual with the virus can infect, and the viral strains present.
The researchers tested the model against official influenza surveillance systems and found it accurately forecast the disease's evolution up to six weeks in advance.
In analyzing the 2014-2015 and 2015-2016 flu seasons in the U.S., Italy, and Spain, the researchers applied forecasting and other algorithms week by week to the key parameters informed by the Twitter data. "By capturing the key parameters, we could track how serious the flu was each year compared with every other year and see what was driving the spread," says Northeastern's Qian Zhang.
From Northeastern University News
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found