Darker red indicates higher reports of flu cases culled from Twitter data. Clearly, 2013 (lower map) is having a more intense flu season that 2012 (upper map).
Darker red indicates higher reports of flu cases culled from Twitter data. Clearly, 2013 (lower map) is having a more intense flu season that 2012 (upper map).

I’m lucky enough to be flu-free as I write this blog post; not so much pretty everyone else in America. (Sorry! Take the Tamiflu, it really works!) Public health researchers at John Hopkins have found a surprisingly useful tool to help them track the disease as it spreads throughout the country, one that works even better than the traditional method of compiling medical information in government databases:  Twitter.

By scanning Twitter and other social media sites for key words (like “flu” or “sick”), researchers can get a swift picture of where and how intensely the flu is spreading. And thanks to input from the Hopkins computer science department, they’re now even better at sifting the real reports of illness from ambient (and misleading) chatter. “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,” computer scientist Mark Dredze told the JHU Hub. “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.”

For example, a recent spike in flu talk on Twitter didn’t actually correlate with more cases of the virus; it was actually just a bunch of people wondering whether Kobe Bryant had the flu during a recent basketball game. To separate the signal from the noise, Dredze and his team created a system of algorithms based on human language processing, one that’s so sophisticated it can tell the difference between someone saying “I have the flu” and “I’m worried about getting the flu.”

“This new work demonstrates that Twitter posts can be used to guide public health officials in their response to outbreaks of infectious diseases,” Dredze told the Hub. “Our hope is that the new technology can be used track other diseases as well.”

Guess how many times President Obama mentioned God in Monday’s inaugural address? (The answer is at the bottom of this post). Before you make your guess, consider that our nation’s earliest presidents — including George Washington, John Adams, Thomas Jefferson, and James Madison — never mentioned God in their inaugurals, according to Goucher religion professor Ann Duncan.

By studying presidents’ references to God in these speeches, Duncan told NPR this week, we can get a sense of the role that religion played in their lives, and track changes over time. For the Revolutionary Era presidents, Duncan says, God was “a rather distant … but still very providential and powerful force. Not the kind of personal god that an evangelical Christian today might talk about.”

That changed for various reasons, including the growing prominence of Protestantism and its more individualized conception of God. Since World War Two, every president has invoked God during his inaugural:  George W. Bush did it 3 times in each address, while Ronald Reagan holds the record (8 times, in his second address). Obama’s count? A robust five.