Community detection and tracking in social network is an important research area for many applications which are widely applied in complex systems. Recently there has been a surge of investigation in this area, fueled largely by interest in social networks, but also by interest in bibliographic citations and telecommunication records. However, due to the computational cost of the traditional algorithm for large-scale networks, most of them are not applied to industrial applications. In this paper, we present a novel framework, as CommTrend, for uncovering the community structure of networks. Our method not only has a prominent advantage over the efficiency but also can effectively reveal the underlying community structures. With respect to real-world application, our algorithm is applied to several massive datasets. Moreover, we integrate CommTrend into a bibliographical service system. By employing it to a large-scale bibliographical dataset, we demonstrate the comprehension of our work and its effectiveness for practical problems.