Twin Peaks, a Stochastic Model for Recurring Cascades
Abstract
Understanding information dynamics and their resulting cascades
is a central topic in social network analysis. In a recent seminal
work, Cheng et al. analyzed multiples cascades on Facebook over
several months, and noticed that many of them exhibit a recurring
behaviour. They tend to have multiple peaks of popularity, with
periods of quiescence in between.
In this paper, we propose the first mathematical model that
provably explains this interesting phenomenon. Our model is simple
and shows that it is enough to have a good clustering structure
to observe this interesting recurring behaviour with a standard
information diffusion model. Furthermore, we complement our
theoretical analysis with an experimental evaluation where we
show that our model is able to reproduce the observed phenomenon
on several social networks.