Mining content for early threat detection
Abla Mawudeku, chief of the Global Public Health Intelligence Network (GPHI) of the Centre for Emergency Preparedness and Response in Canada, and her team use the latest technology to detect threats to human life. Those can include such risks as the H1N1 virus, also known as "swine flu."
To spot potential problems, multilingual analysts comb through content from many sources worldwide--including news aggregators like Factiva--that has been parsed from about 1,000 concepts such as "mysterious ailments" and "outbreak."
The GPHIN uses Nstein’s TME (Text Mining Engine) to assign a relevancy score to each article, according to a recent news release from Nstein, and TME also de-dupes redundant news articles. The system helps the analysts count and track instances of possible risks, then triggers responses, Nstein says. (In the case of the H1N1 virus, the World Health Organization declared a geographic pandemic, which, in turn, speeds the development of vaccines.)
"The job is a tremendously stressful one," says Mawudeku. "We are normally adding 4,000 articles a day. Right now (during the H1N1 outbreak), we are overwhelmed with more than 20,000 a day. It would be impossible to track this volume without technology."
The GPHIN monitors all man-made and natural threats to human life, not only diseases.