Co-evolutionary Dynamics of Information Diffusion and Network Structure

Information diffusion in online social networks is obviously affected by the underlying network topology, but it also has the power to change that topology. Online users are constantly creating new links when exposed to new information sources, and in turn these links are alternating the route of information spread. However, these two highly intertwined stochastic processes, information diffusion and network evolution, have been predominantly studied separately, ignoring their co-evolutionary dynamics. In this project, we propose a probabilistic generative model, COEVOLVE, for the joint dynamics of these two processes, allowing the intensity of one process to be modulated by that of the other. This model allows us to efficiently simulate diffusion and network events from the co-evolutionary dynamics, and generate traces obeying common diffusion and network patterns observed in real-world networks. Furthermore, we also develop a convex optimization framework to learn the parameters of the model from historical diffusion and network evolution traces. We experimented with both synthetic data and data gathered from Twitter, and show that our model provides a good fit to the data as well as more accurate predictions than alternatives.