One Per Cent

Twitter helps track cholera spread in Haiti

Niall Firth, technology editor
(Image: Sipa Press/Rex Features)

When disaster strikes, Twitter is always the first to know.

Now a new study has demonstrated that using Twitter updates and online news websites to track a disease outbreak is not only quicker than more traditional methods - it's just as reliable, too.

In a study published in the January issue of the American Journal of Tropical Medicine and Hygiene, researchers studied the progression of a cholera epidemic in Haiti after the
devastating earthquake in 2010.

The study's lead author Rumi Chunara, a research fellow at Harvard Medical School, used an piece of software called HealthMap to monitor how many times the epidemic was mentioned online during the first 100 days of the outbreak - from October 20, 2010 to January 28, 2011. Her research team also looked at the number of posts on Twitter that mentioned the word cholera.

They discovered 4697 online reports via HealthMap in eight different languages, and 188,819 tweets. Using this data they were able to monitor how the outbreak was progressing. They found that information gleaned from online sources in this way closely matched the official reports, gathered by surveying hospitals and health clinics. The only difference - and huge advantage - was that the online data was available in almost real time, nearly two weeks before the official reports from the govenerment health ministry were available.

"The techniques we employed eventually could be used around the world as an affordable and efficient way to quickly detect the onset of an epidemic and then intervene with such things as vaccines and antibiotics," says Chunara, who works at the Children's Hospital Boston.

The cholera epidemic in Haiti has already killed more than 6500 people, according to the study.

Twitter data has been mined in the past to track vaccinations in the US as well as the progress of diseases such as the swine flu pandemic in 2009 and the annual dengue fever outbreak in Brazil.

http://www.newscientist.com/