A Co-Evolution Model of Network Structure and User Behavior : The Case of Content Generation in Online Social Networks

With the rapid growth of online social network sites (SNS), it has become imperative for platform owners and online marketers to quantify what factors drive content production on these platforms. Previous research identified challenges in modelling these factors statistically using observational data where the challenges stem from the inability to disentangle the effects of network formation and network influence on content generation, and the subsequent feedback on network structure, using conventional methods. In this paper, we adopt and enhance an actor-oriented continuous-time statistical model that enables the joint estimation of the co-evolution of the users' social network structure and the amount of content they produce, using a Markov Chain Monte Carlo (MCMC)-based simulation approach. Specifically, we offer a method to analyze non-stationary and continuous behavior in the presence of network effects and observable and unobservable covariates, similar to what is observed in social media ecosystems. We apply our model to social network data on university students over six months to find that: 1) users tend to connect with others that have similar posting behavior, 2) however, after doing so, users tend to diverge in posting behavior, and 3) peer influences are sensitive to the strength of the posting behavior. More broadly, our method provides researchers and practitioners with a statistically rigorous approach to analyze network effects in observational data. These results provide insights and recommendations for SNS platforms to sustain an active and viable community