Affiliations: [a] Shandong Province Key Laboratory of Wisdom Mine Information Technology, College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong, China | [b] Qilu University of Technology/Shandong Academy of Sciences, Jinan, Shandong, China | [c] Information Research Institute of Shandong Academy of Sciences, Jinan, Shandong, China
Correspondence:
[*]
Corresponding author: Shiwei Zhu, Qilu University of Technology/Shandong Academy of Sciences; Information Research Institute of Shandong Academy of Sciences, Jinan, Shandong 250014, China. E-mail: sc_zsw@163.com.
Abstract: Influence maximization (IM) is a problem of selecting k nodes from social networks to make the expected number of the active node maximum. Recently, with the popularity of Internet technology, more and more researchers have paid attention to this problem. However, the existing influence maximization algorithms with high accuracy are usually difficult to be applied to the large-scale social network. To solve this problem the paper proposes a new algorithm, called community-based influence maximization (ComIM). Its core idea is “divide and conquer”. In detail, this algorithm first utilizes the Louvain algorithm to divide the large-scale networks into some small-scale networks. Afterwards, the algorithm utilizes the one-hop diffusion value (ODV) and two-hop diffusion value (TDV) functions to calculate the influence of a node and select nodes on these small-scale networks, which can improve the accuracy of our proposed algorithm. By using the above methods, the paper proposes a community influence-estimating method called CDV, which can improve the efficiency of the algorithm. Experimental results on six real-world datasets demonstrate that our proposed algorithm outperforms all comparison algorithms when comprehensively considering the accuracy and efficiency.
Keywords: Social networks, influence maximization, community detection, influence estimating method
