Abstract: Communities, especial overlapping communities in complex networks are significant in many fields such as in- formation spreading and recommending,public opinion controlling,and commercial marketing. Overlapping communities detecting is attracting increasing attentions since some nodes may naturally belong to several groups in real-world net- works. This paper proposed an overlapping community detecting algorithm based on two phase strategies; initial com- munity extracting and community merging. In extracting phase, a node with maximal degree and its tight neighbors arc selected as an initial community, and nodes tight with the community arc also included. In merging phase, two communi- ties are merged if the modularity gets larger after merging. Three real-world complex networks including a large-scale one were used to evaluate the algorithm. Experimental results demonstrate that the proposed algorithm is efficient for detecting overlapping communities in complex networks.

Key words: Complex network, Overlapping community, Community extracting and merging, Connecting degree