Understanding User Migration Patterns in Social Media

Kumar, Shamanth; Zafarani, Reza; Liu, Huan
Proceedings of the AAAI Conference on Artificial Intelligence

The incredible growth of the social web over the last decade has ushered in a flurry of new social media sites. On one hand, users have an inordinate number of choices; on the other hand, users are constrained by limited time and resources and have to choose sites in order to remain social and active. Hence, dynamic social media entails user migration, a well studied phenomenon in fields such as sociology and psychology. Users are valuable assets for social media sites as they help contribute to the growth of a site and generate revenue by increased traffic. We are intrigued to know if social media user migration can be studied, and what migration patterns are. In particular, we investigate whether people migrate, and if they do, how they migrate. We formalize site and attention migration to help identify the migration between popular social media sites and determine clear patterns of migration between sites. This work suggests a feasible way to study migration patterns in social media. The discovered patterns can help understand social media sites and gauge their popularity to improve business intelligence and revenue generation through the retention of users.