A Simple and Effective Community Detection Method Combining Network Topology with Node Attributes

Community detection is a fundamental problem in the study of complex networks. So far, extensive approaches, which use network topology alone or use both network topology and attribute information, have been designed to detect the community partitions of networks. However, existing approaches cannot work effectively for networks whose community structure does not match well with the ground-truth, or networks whose topological information contains serious noise, and networks where the difference of attribute similarity between nodes is tiny. Inspired by a force-directed network layout and community intuitive characteristics, we propose a simple while effective approach which utilizes attribute information to partition nodes into communities by maximizing network modularity. By using attributes as nodes to the network and the interaction between nodes, our novel method cannot only effectively improve community detection of networks, but also obtain the number of communities closer to the real one. Through extensive experiments on some real-world datasets, we demonstrate the superior performance of the new approach over some state-of-the-art approaches.