Abstract

Objective Social media exhibit rich yet distinct temporal dynamics which cover a wide range of differ-ent scales. In order to study this complex dynamics, two fundamental questions revolve around (1) the signatures of social dynamics at different time scales, and (2) the way in which these signatures interact and form higher-level meanings. Method In this paper, we propose the Recursive Convolutional Bayesian Model (RCBM) to address both of these fundamental questions. The key idea behind our approach consists of con-structing a deep-learning framework using specialized convolution operators that are de-signed to exploit the inherent heterogeneity of social dynamics. RCBM’s runtime and convergence properties are guaranteed by formal analyses. Results Experimental results show that the proposed method outperforms the state-of-the-art ap-proaches both in terms of solution quality and computational efficiency. Indeed, by applying the proposed method on two social network datasets, Twitter and Yelp, we are able to iden-tify the compositional structures that can accurately characterize the complex social dynam-ics from these two social media. We further show that identifying these patterns can enable new applications such as anomaly detection and improved social dynamics forecasting. Fi-nally, our analysis offers new insights on understanding and engineering social media dy-namics, with direct applications to opinion spreading and online content promotion.