Analysis of the Evolution of the Influence of Central Nodes in a Twitter Social Network

Both practitioners and researchers are becoming increasingly interested in viral marketing. For viral marketing on social media, it is important to find influencers who can spread information to many other users. Although finding influencers on social media is a topic of much research interest in the field of network science, most previous studies ignored the time evolution of the influence of social media users. In this paper, we investigate the time evolution of the influence of Twitter users. We construct a social network of 0.3 million Twitter users, extract the central nodes in the network using five centrality measures, and investigate how the actual influence of those central nodes changes over a year. We show that the overlap between the central nodes and actual influencers did not change drastically during the one-year period, suggesting that the influence of central nodes is stable over time.