Mining research community on the basis of hidden relationships present between its entities is important from academic recommendation point of view. Previous approaches discovered research community by using network connectivity based distance measures (no text semantics) or by using poorer text semantics and relationships of documents DL (Document Level) by ignoring richer text semantics and relationships of VL (Venue Level). In this paper, we address this problem by considering richer text semantics and relationships. We propose a VAT (Venue Author Topic Approach) based on Author-Topic model to discover inherent community structures in a more realistic way by modeling from VL. We show how topics and authors can be inferred for new venues and how author-to-author and venue-to-venue correlations can be discovered. The positive relationship of topic denseness with ranking performance of proposed approach is explained. Experimental results on research collaborative network \"DBLP\" demonstrate that proposed approach significantly outperformed the baseline approach in discovering community structures and relationships in large-scale network.