Using social network analysis to detect conspiracies

• Main Author: Ho, Grace Wei Ching.
• Other Authors: School of Computer Engineering
• Format: Final Year Project
• Language: English
• Published: 2011
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
• Online Access: http://hdl.handle.net/10356/43573
• Institution: Nanyang Technological University

Social Network Analysis (SNA) examines the structure of social relationships in a network to uncover the informal connections between people whilst analysing interpersonal relationships. This project aims to utilise various SNA metrics such as Density and Average Path Length (APL) to quantify different aspects of a group's communication pattern, in particular, networks displaying suspicious terrorist activities, like Leninist and Maoist cell organizations. Since the onslaught of terrorist organizations and their illicit activities occuring all over the world, for example, the 9/11 bombings in USA and 7/7 London attacks, there is increasing concern over the homeland security of countries and their citizens. Numerous amounts of graph data have been analyzed by experts in an attempt to learn more about such organizations to prevent future attacks. In this project, we introduce the concept of Graph Theory in analyzing social networks, coupled with using SNA metrics in an attempt to detect terrorist networks. Networks of small-world evolution are compared to those exhibiting the hub-and-spoke evolution, a common pattern of terrorists groups. Pattern mining was also introduced as it is a crucial part of this project. We concluded that it is indeed possible to detect terrorist cell organizations apart from normal social networks using pattern classification.