A research group led by scientists in Brazil has developed software that tracks outbreaks of dengue fever using the social media outlet twitter. This software was created thanks to coordination between two Brazilian National Institutes of Science and Technology, led by Wagner Meira, a computer scientist at the Federal University of Minas Gerais.

The software is designed to detect the word “dengue” in tweets and information about the sender’s location. The software analyzes the sentence structure and wording to determine if tweets are appropriate for dengue surveillance. Tweets that are deemed spurious or unrelated to dengue fever are filtered out.

During the testing phase, the researchers examined 2,447 tweets about dengue fever sent through the social networking portal between January and May 2009. They found a strong correlation between personal experience tweets about dengue and official data on outbreaks from the Brazilian Ministry of Health.

The research team now plans to analyze 181,845 tweets sent between December 2010 and April 2011, but are waiting for the ministry’s 2011 data before they do so. They also plan to incorporate other key words, mostly symptoms of dengue fever, into their detection scheme to gather more tweets.

This is the first time social media has been used for dengue fever surveillance, but it is not the first time social media has been used for real-time epidemic surveillance. Twitter was used to follow the 2009 swine flu pandemic. Furthermore, it is the first attempt to gather information on people tweeting about their personal experience of a disease.

Google also introduced Google Dengue Trends last month, which records spikes in web searches for dengue fever. Therefore, using social media for surveillance is not a new practice, and nor is tracking dengue using technology. However, Meira’s method is an innovative and efficient way to track dengue fever.

Dengue fever, which can cause hemorrhagic deaths, plagues Brazil ever year. Moreover, every year it emerges in different locations than before. Most Brazilians know how to control and even eradicate the disease, but the majority of citizens don’t take any precautions against it.

On top of that, outbreak notifications take several weeks to process and analyze which impedes officials from assisting citizens. Using Twitter messages could mean a much faster response, says Meira. “It isn’t predicting the future but the present,” he says. “This means we aren’t weeks behind like we used to be.”