The evolution of influence through endogenous link formation

Abstract

© 2018 INFORMS. Marketing researchers and practitioners are interested in targeting individuals in social networks who may have disproportionately higher levels of influence over others in their network. While the extant literature suggests individual characteristics or network position as proxies for relative influence, our study bridges these two streams by investigating the endogenous acquisition of network position as a function of exogenous individual characteristics. Specifically, do those with higher expertise achieve higher influence when people endogenously choose those to whom they listen? Using an agent-based modeling simulation framework, we model the dynamics of two types of individuals, i.e., independents with exogenous information and imitators. Over the course of multiple diffusions, agents choose whom to "listen to" for information; dropping less useful ties and adding new ones. We find that independents can have less influence (out-degree) than imitators who collect information from multiple sources. Furthermore, this effect is exacerbated by homophily. Noise in communication channels, on the other hand, moderates these effects, yet can increase penetration rates. We show that our results are robust to alternative dynamic network structures. Our research suggests that marketers should consider the environment, community characteristics, communication medium, and product domains when assessing the relative influence of individuals.