In an interview on today’s Weekend Edition, (NPR) scientists at John’s Hopkins told how they are successfully tracking flu outbreaks by analyzing tweets. They said the program and algorithms they developed can differentiate between someone saying they have the flu (or flu symptoms) and someone worried about getting the flu. They also claimed their accuracy is supported by health records.
One potential use of the data is that by pinpointing flu outbreaks, hospitals would know in advance when to increase staff levels and order extra supplies. Doing so could increase the number of patients seen sooner, thereby reducing the spread of the disease. This is an amazing use of social media to help treat and even prevent flu outbreaks.
There is no link to that interview on NPR's website. Using Google to search for a link to the article returned more than 20 million links to similar articles published over the last several years. It turns out that tweets are being successfully used to track all kinds of diseases!
An EWEEK article Twitter Becomes Flu-Tracking Tool for Johns Hopkins Researchers says that “Computer scientists at Johns Hopkins University are using Twitter to track the number of flu cases in the United States.” This was for the 2012/2013 winter flu season. Apparently they've perfected the process for this year.
On Plos One, a study tracking the A H1N1 Pandemic of 2011 determined that: “By virtue of sheer volume, content embedded in the Twitter stream may be useful for tracking or even forecasting behavior if it can be extracted in an efficient manner. In this study, we examine the use of information embedded in the Twitter stream to (1) track rapidly-evolving public sentiment with respect to H1N1 or swine flu, and (2) track and measure actual disease activity. We also show that Twitter can be used as a measure of public interest or concern about health-related events. Our results show that estimates of influenza-like illness derived from Twitter chatter accurately track reported disease levels.”*
Then, according to the Huffington Post, Brigham Young University professor Christophe Giraud-Carrier, with the help of his computer science students, used the GPS feature on twitter coupled with actual references to symptoms in tweets to prove twitter could be used to track all kinds of diseases. “They examined about 24 million tweets from 10 million different users” and “examined the frequencies of the tweets, as well as the content of the tweets to see if the Twitter users talked about any symptoms.” By creating a map of reported illnesses they determined twitter could be used to track and even prevent many diseases.
So, the next time you feel ill, either physically or mentally, and you tweet about it, you could be helping researchers to more efficiently track, treat and/or prevent disease. That means that if you live in the Hudson Valley or Catskill Mountains, your tweets could help to keep your neighbors healthy.
And rest assured, the day cannot be far off when @dr-bot replies to your #flu tweet with this advice: “Stay inside, get plenty of fluids and rest, and call your doctor if the symptoms persist or intensify.”
*Signorini A, Segre AM, Polgreen PM (2011) The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic. PLoS ONE 6(5): e19467. doi:10.1371/journal.pone.0019467