Term of Award

Spring 2014

Degree Name

Master of Science in Applied Engineering (M.S.A.E.)

Document Type and Release Option

Thesis (restricted to Georgia Southern)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


Department of Computer Sciences

Committee Chair

Christopher Kadlec

Committee Member 1

Aimao Zhang

Committee Member 2

Cheryl Aasheim


Amidst the growing use of social media platforms as actively redundant communication channels, emergency alerting via this pathway is in a position to gain from a more automated and systematic usage approach. The corresponding growth of geographic information systems/services (GIS) in local government agencies and the maturing of social media platforms into functional components of our everyday lives both contribute to the opportunity to create an optimal linkage of online social networking and emergency management resources. This paper proposes a method for which municipalities can use their robust geographic feature datasets along with location prediction techniques for labeling non geo-located social media users as local citizens and potential recipients of critical messages. The breadth of location inference research as well as the complementary aspects of location disambiguation is examined to discover a novel combination of methods suitable for supplementing geographic prediction in social media with regional geographic datasets. Furthermore, a system is proposed which aims to effectively integrate GIS, social media and emergency management resources in order to meet the demand for a modern mass notification infrastructure.