Beyond network centrality: Individual-level behavioural traits for predicting and seeding information spreading in social media

Abstract Understanding the heterogeneous role of individuals for large-scale information spreading is essential to manage online behaviour as well as its potential offline consequences. To this end, most existing studies from diverse research domains focus on the disproportionate role played by highly-connected “hub” individuals. However, we demonstrate here that information spreading in online social media is best understood and predicted by simultaneously uncovering two individual-level behavioural traits: influence and susceptibility. Specifically, we derive a nonlinear network-based algorithm to quantify individuals’ influence and susceptibility from multiple spreading event data. By applying the algorithm to large-scale data from Twitter and Weibo, we demonstrate that both individuals’ influence and susceptibility are key determinants of peer-to-peer information propagation: neglecting one of the two properties leads to sub-optimal propagation predictions. We show that, as a consequence, considering both properties can significantly improve seeding policies aimed at broadly disseminating information.