A research project is being proposed to investigate and formulate a novel real-time
infectious disease detection/surveillance model that will use spatial, temporal, and text
mining of crowd-sourced data and Twitter data for Mauritius. The real-time analysis results
will be reported visually in terms of disease surveillance maps: distribution and timeliness
of the disease will be shown. Such a system can be very useful for early detection and
prediction of seasonal disease outbreaks. The resulting insights are expected to reduce the
response time in case of a pandemic, as well as help in tracking the spread of an infectious
disease in Mauritius.
The proposed research work will investigate social media data ETL (Extract-TransformLoad) methods, and propose a model for visualizing outbreaks and the spread of an
infectious disease in space and time. A prototype will be developed using rich information
retrievable in real time from Twitter and a crowd-sourced mobile application. Since the
system will be completely automated and the output of analysis will be updated near real
time, it is expected to detect disease outbreaks significantly faster than the traditional
disease surveillance system that collects public health data from sentinel medical practices.
The resulting application has the potential for being developed into a real-time and online
application that can be used for tracking infections in Mauritius, and later extended to the
neighboring Indian Ocean islands and in the African continent.