Leveraging Behavioral Factorization and Prior Knowledge for Community Discovery and Profiling

Recently community detection has attracted much interest in social media to understand the collective behaviours of users and allow individuals to be modeled in the context of the group. Most existing approaches for community detection exploit either users' social links or their published content, aiming at discovering groups of densely connected or highly similar users. They often fail to find effective communities due to excessive noise in content, sparsity in links, and heterogenous behaviours of users in social media. Further, they are unable to provide insights and rationales behind the formation of the group and the collective behaviours of the users. To tackle these challenges, we propose to discover communities in a low- dimensional latent space in which we simultaneously learn the representation of users and communities. In particular, we integrated different social views of the network into a low-dimensional latent space in which we sought dense clusters of users as communities. By imposing a Laplacian regularizer into affiliation matrix, we further incorporated prior knowledge into the community discovery process. Finally community profiles were computed by a linear operator integrating the profiles of members. Taking the wellness domain as an example, we conducted experiments on a large scale real world dataset of users tweeting about diabetes and its related concepts, which demonstrate the effectiveness of our approach in discovering and profiling user communities.