Crandall, David, et al. "Feedback effects between similarity and social influence in online communities." Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining. 2008.

This study investigates the dynamic interplay between similarity and social ties within online social networks, focusing on the dual processes of social influence and selection. Social influence refers to individuals becoming more like their friends over time, while selection involves forming connections with others who are already similar. The research employs innovative techniques to analyze data from online communities, revealing feedback loops where rising similarity between individuals predicts future interactions, which in turn lead to further increases in similarity, albeit at a diminished rate. Additionally, the study examines the predictive power of similarity and social influence on forecasting an individual's future activities, questioning whether the activities of a person's friends or those of similar individuals are more indicative of future behavior.