Start Date
12-13-2015
Description
Estimating the impact of network effects on content production and friendship formation on social network sites (SNS) is of key importance to the platforms owners and online advertisers. However, past research on modeling network effects using observational data is limited by their inability to separate the effects of network formation from network influence. In the current study, we adapt an actor-based continuous-time model to jointly estimate the co-evolution of the users' social network and their content production behavior using a Markov Chain Monte Carlo (MCMC) based approach. Our analysis on a dataset of university students reveals that: 1) users tend to connect with others with similar posting behavior, 2) however, after connecting, they gradually diverge from their peers, and 3) the network effects are moderated by the level of the posting behavior. Our findings offer useful insights about the role of network effects to platform owners and social network researchers.
Recommended Citation
Bhattacharya, Prasanta; Phan, Tuan; and Airoldi, Edoardo, "Investigating the Impact of Network Effects on Content Generation: Evidence from a Large Online Student Network" (2015). ICIS 2015 Proceedings. 12.
https://aisel.aisnet.org/icis2015/proceedings/SocialMedia/12
Investigating the Impact of Network Effects on Content Generation: Evidence from a Large Online Student Network
Estimating the impact of network effects on content production and friendship formation on social network sites (SNS) is of key importance to the platforms owners and online advertisers. However, past research on modeling network effects using observational data is limited by their inability to separate the effects of network formation from network influence. In the current study, we adapt an actor-based continuous-time model to jointly estimate the co-evolution of the users' social network and their content production behavior using a Markov Chain Monte Carlo (MCMC) based approach. Our analysis on a dataset of university students reveals that: 1) users tend to connect with others with similar posting behavior, 2) however, after connecting, they gradually diverge from their peers, and 3) the network effects are moderated by the level of the posting behavior. Our findings offer useful insights about the role of network effects to platform owners and social network researchers.