Predicting Social Influence Based on Dynamic Network Structures

This study examines how network structure and dynamics interplay with the effect of social influence to facilitate diffusion. The context we consider is the diffusion of a new smartphone from a major wireless carrier in two medium-sized cities in China. The study is carried out in three stages: (1) New phone adopters (seeds) are selected within our sample period, and a two-layer snowball sampling of their mobile contacts is used to extract individual networks. (2) Given longitudinal networks and temporal adoption behaviors, the stochastic actor-based dynamic network model is used to determine the homophily effect on network formation and the social influence effect on adoptions. (3) The measures of the network structure are linked to the estimated effects of social influence based on meta-analysis. As a result, the two most significant network measures related to social influence are diversity of connection and time variation of edge numbers, after controlling for network size and density. The simulation further reveals that a certain amount of initial adopters is needed to trigger positive social influence during the diffusion process. Our findings provide a new perspective on buzz marketing campaigns by emphasizing the appropriate selection of social networks prior to the selection of individuals