NEW YORK, NY (Catholic Online) - Mapping the flu in real time across New York City, Adam Sadilek of the University of Rochester created an algorithm that scanned the news feeds of Twitter users for one month in 2010. After filtering out the "I'm sick of this job" and "I'm sick of this relationship" tweets, Sadilek was able to determine who was sick and who wasn't.

More interestingly. He could predict who would get sick next. 

Oh his website, Sadilek explained how it worked, "Given that three of your friends have flu-like symptoms, and that you have recently met eight people, possibly strangers, who complained about having runny noses and headaches, what is the probability that you will soon become ill as well? Our models enable you to see the spread of infectious diseases, such as flu, throughout a real-life population observed through online social media."

The secret is that tweets are GPS tagged, so anyone with the right software can see precisely where the sender was when the tweet was posted. Sadilek continues, "We apply machine learning and natural language understanding techniques to determine the health state of Twitter users at any given time. Since a large fraction of tweets is geo-tagged, we can plot them on a map, and observe how sick and healthy people interact. Our model then predicts if and when an individual will fall ill with high accuracy, thereby improving our understanding of the emergence of global epidemics from people's day-to-day interactions."

Sadilek claims his algorithm is 90 percent accurate. 

Common sense is normally enough to tell us when we're due for the cold or flu. We can generally tell when the people around us are ill, and if we have spent enough time near them to contract an illness, so we don't need Twitter to warn us to stock up on aspirin and tissues. But the data is useful for people studying macro-trends in disease. In other words, if the algorithm works, it could be used to chart the outbreak and progression of flu epidemics. 

Understanding how these diseases spread and where they will show up next is critical information that can help officials fight illness more efficiently. 

However, what about privacy concerns? Sadilek and his team are silent about those, but that wasn't a goal of the project. In the long term, however, such technology could be used to serve relevant ads before an illness reaches a community. It could also potentially be used to track more than illness. On his website Sadilek talks about predicting human behavior and optimizing strategies using GPS tracking. 

Such knowledge would have both social, commercial, and military usefulness. 

As with all tools and gadgets, it's how we choose to use them that makes the world a better place, or worse. If we use Sadilek's algorithms to fight illness, we will have made the world a better place. But if we turn suck knowledge to evil use, well-the good news is, it's up to us. 

We wonder if Big Brother already knows...
© 2012, Distributed by NEWS CONSORTIUM.