Information contagion in temporal human networks with heterogeneous susceptibility

Abstract

Information Cascades are propagation patterns in human networks where information such as political propaganda, rumors, or fashion trends, emanate from one or more starting points and are either accepted or rejected by each connected member of a community. The decisions made by individuals either govern a large ripple through the community, or prevent significant changes from occurring, making Information Cascades of avid interest within economics and network science. Since Information Cascades have similar behavior to the well studied field of epidemiology, many Cascades are modeled with disease propagation models like the Susceptibility, Infection, and Recovery (SIR) model. In this thesis we argue that such generic models are insufficient for predicting information spread in human behavioral networks, because they do not represent temporal availability of communication and individual variations in susceptibility to peer-pressure. We propose a new model wherein agents have heterogeneous activity periods and activation thresholds, representing individual susceptibility to peer-pressure. By applying this model to networks with a range of topologies, as well as real-world networks, we are able to more accurately represent human behavior in a variety of communities.