A Longitudinal Study of Follow Predictors on Twitter
A Longitudinal Study of Follow Predictors on Twitter, by C.J. Hutto, Sarita Yardi, Eric Gilbert. CHI 2013, April 27 May 2, 2013, Paris, France. Copyright 2013 ACM 978-1-4503-1899-0/13/04.
“Follower count is important to Twitter users: it can indicate popularity and prestige. Yet, holistically, little is understood about what factors like social behavior, message content, and network structure lead to more followers.Such information could help technologists design and build tools that help users grow their audiences. In this paper, we study 507 Twitter users and a half-million of their tweets over 15 months. Marrying a longitudinal approach with a negative binomialauto-regression model, we find that variables for message content, social behavior, and network structure should be given equal consideration when predicting link formations on Twitter. To our knowledge, this is the first longitudinal study of follow predictors, and the first to show that the relative contributions
of social behavior and message content are just as impactful as factors related to social network structure for predicting growth of online social networks. We conclude with practical and theoretical implications for designing social media technologies.”