Posted by: bluesyemre | March 2, 2013

A Longitudinal Study of Follow Predictors on Twitter

  • 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 study507 Twitter users and a half-million of their tweets over 15months. Marrying a longitudinal approach with a negative binomial auto-regression model, we find that variables formessage 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 showthat 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.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.


%d bloggers like this: