Social network change detection using a genetic algorithm based back propagation neural network model

Abstract

Changes in social networks may reflect an underlying significant events or behaviors within an organization. Detecting these changes effectively and efficiently could have the potential to enable the early warning, and faster response to both positive and negative organizational activities. In this paper, we use a genetic algorithm based back propagation (GABP) neural network model to quantitatively determine if and when a change has occurred. By selecting network measures as input and dynamic network behavior types as output, we get the GABP neural network model well trained. Then, this approach is applied to Enron social networks. The results indicate that this approach achieves higher detection precision.