Leveraging Motifs to Model the Temporal Dynamics of Diffusion Networks

Abstract

Information di usion mechanisms based on social in uence models are mainly studied using likelihood of adoption when active neighbors expose a user to a message. e problem arises primarily from the fact that for the most part, this explicit information of who-exposed-whom among a group of active neighbors in a social network, before a susceptible node is infected is not available. In this paper, we a empt to understand the di usion process through information cascades by studying the temporal network structure of the cascades. In doing so, we accommodate the e ect of exposures from active neighbors of a node through a network pruning technique that leverages network motifs to identify potential infectors responsible for exposures from among those active neighbors. We a empt to evaluate the e ectiveness of the components used in modeling cascade dynamics and especially whether the additional e ect of the exposure information is useful. Following this model, we develop an inference algorithm namely I C , that uses parameters learned from the model and the exposure information to predict the actual parent node of each potentially susceptible user in a given cascade. Empirical evaluation on a real world dataset from Weibo social network demonstrate the signi cance of incorporating exposure information in recovering the exact parents of the exposed users at the early stages of the di usion process.

Use of a controlled experiment and computational models to measure the impact of sequential peer exposures on decision making

“…The opaque nature of the effect of exposures in the real world responsible for influence makes it more difficult to analyze the characteristics of these PoI. The fact that the data about who-exposed-whom in real world information cascades is rarely available makes studying peer influence more challenging [16]. To this end, we tried to bridge the gap between experimental hypothesis and real-world scenarios by modeling the behavior of agents or users when subject to peer influences and by capturing the sequential nature and bursts in influences towards diffusion.…”

“…However what is often understudied or left out in these research studies is the sequential exposure mechanism or what we refer to as PoI in the paper. Additionally, observing and mapping these PoI in the real world to analyze the cause and effect synopsis is not straightforward because of the opacity problem [16].…”