Abstract

Studying temporal dynamics of topics in social media is very use-ful to understand online user behaviors. Most of the existing work on this subject usually monitors the global trends, ignoring vari-ation among communities. Since users from different communi-ties tend to have varying tastes and interests, capturing community-level temporal change can improve the understanding and manage-ment of social content. Additionally, it can further facilitate the ap-plications such as community discovery, temporal prediction and online marketing. However, this kind of extraction becomes chal-lenging due to the intricate interactions between community and topic, and intractable computational complexity. In this paper, we take a unified solution towards the community-level topic dynamic extraction. A probabilistic model, CosTot (Com-munity Specific Topics-over-Time) is proposed to uncover the hid-den topics and communities, as well as capture community-specific temporal dynamics. Specifically, CosTot considers text, time, and network information simultaneously, and well discovers the inter-actions between community and topic over time. We then dis-cuss the approximate inference implementation to enable scalable computation of model parameters, especially for large social data. Based on this, the application layer support for multi-scale tempo-ral analysis and community exploration is also investigated. We conduct extensive experimental studies on a large real mi-croblog dataset, and demonstrate the superiority of proposed model on tasks of time stamp prediction, link prediction and topic perplex-ity. 1.