Detecting Public Health Indicators from the Web for Epidemic Intelligence

Abstract

Recent pandemics such as Swine Flu, have caused concern for public health officials. Given the ever increasing pace at which infectious diseases can spread globally, officials must be prepared to react sooner and with greater epidemic intelligence gathering capabilities. However, state-of-the-art systems for Epidemic Intelligence have not kept the pace with the growing need for more robust public health event detection. In this paper, we propose an approach that shifts the paradigm for how public health events are detected. Instead of manually enumerating linguistic patterns to detect public health events in human language text (pattern matching); we propose the use of a statistical approaches, which instead learn the patterns of public health events in an automatic or unsupervised way.