Explore semantic topics and author communities for citation recommendation in bipartite bibliographic network

Citation recommendation is the task of suggesting a list of references for an author given a manuscript. This is important for academic research for it provides an efficient and easy way to find relevant literatures. In this paper, we propose a novel probabilistic topic model to automatically recommend citations for researchers. The model considers not only text content similarity between papers but also community relevance among authors for effective citation recommendation. To fully utilize content and diversified link information in a bibliographic network, we extend LDA with matrix factorization, so that semantic topic learning and community detection are essentially reinforcing each other during parameter estimation. We also develop a flexible way to generate a family of citation link probability functions, which can substantially increase the model capacity. Experimental results on the ANN and DBLP dataset show that our model outperforms baseline algorithms for citation recommendation, and is capable of generating qualified author communities and topics.