The 2013 flu epidemic is the worst seasonal flu outbreak in 10 years, according to the CDC – so how are researchers, doctors, and even insurance companies tracking the spread of the disease around the country? Social Media and Google. Johns Hopkins University released the successful results of a project to track flu symptoms via Twitter January 28, 2013 – and a recent statement by Aetna CEO Mark Bertolini reveals that the insurance giant uses Google Flu Trends to track the flu. Flu season will never be the same.
Flu symptoms and Twitter
The biggest problem with using social media to track the spread of the flu, according to researchers at Johns Hopkins University, is that there’s a lot of flu-related chatter to sift through. According to the University’s press release,
“When you look at Twitter posts, you can see people talking about being afraid of catching the flu or asking friends if they should get a flu shot or mentioning a public figure who seems to be ill,” said Mark Dredze, an assistant research professor in the Department of Computer Science who uses tweets to monitor public health trends. “But posts like this don’t measure how many people have actually contracted the flu. We wanted to separate hype about the flu from messages from people who truly become ill.”
Google Flu Trends
Google’s flu trends map has been around since the 2009 H1N1 pandemic, and is getting better at tracking the spread of the flu every year. This fact has not gone unnoticed by those in the health industry, who bear the majority of the costs of a bad flu season. Aetna CEO Mark Bertolini admitted that he keeps an eye on the flu trends map, and it’s likely that he’s not alone – Google’s map gets better at tracking the spread of disease with each update of the algorithm.
Data mining and flu symptoms
So, how do computers sift out the chatter from the genuine flu information? They use a process called data mining, which is becoming more sophisticated all the time. A computer program can analyze huge amounts of data, comparing each piece of information against specified criteria, and return a set of results based on the information you’re looking for.
Computers and health
With today’s machine learning technology, the algorithm that tells researchers how severe this year’s flu season is will get better at analyzing the data with every set of data. Don’t worry about privacy – all personal information is removed from the Tweets; the researchers aren’t tracking your symptoms personally.