Traditional and Deep Learning Approaches to Information and Influence Propagation in Social Networks

Abstract

Social network analysis is an interdisciplinary topic attracting researchers from biology, economics, psychology, and machine learning. It has attracted interests from both the research and business communities for a strong potential and variety of applications. Also, this interest has been fueled by the large success of online social networking sites and the subsequent abundance of social network data produced. An important aspect in this research field is influence maximization in social networks. The goal is to find a set of individuals to be targeted, with the aim to drive social contagion and generate a diffusion cascade. We provide here an overview of the models and approaches used to analyze interaction networks. The challenges this problem introduces are recently being tackled using Deep Learning approaches such as Recurrent Neural Networks (RNNs) which are particularly suited to model sequence inputs.