The roles of network communities in social information diffusion

Online social connections allow users to share and spread information with others. Different users play various roles on information diffusion: some are influential within a community and some make information widely spread across communities. This paper aims to unveil the hidden relationships between nodes and information diffusion in the context of communities from the big Twitter diffusion data with a million-scale social network, as a complement to existing link-based diffusion analysis (e.g. the strength of weak ties). We identify six types of well-known community-aware roles of nodes, and examine their diffusion capability on propagating information within/across communities, using information flows via retweet and mention in Twitter. We find nodes acting as community bridges are exposed to more information and more dominative on spread information within/across communities. Community-aware roles are also validated via supervised learning to be effective for detecting the most diffusive information propagators.