A novel algorithm for mining opinion leaders in social networks

Recently, social network analysis (SNA) has attracted researchers’ attention due to its practicability and popularity. Several mining techniques have been developed for extracting useful knowledge from users’ regularities. Opinion leader discovery is one essential task which has great commercial and political values. By identifying the opinion leaders, companies or governments could manipulate the selling or guiding public opinion, respectively. Additionally, detecting the influential comments is able to understand the source and trend of public opinion formation. However, mining opinion leaders in a huge social network is a challenge task because of the complexity of graph processing and leadership analysis. In this study, a novel algorithm, OLMiner, is proposed to efficiently find the opinion leaders from a social network. OLMiner utilizes a community detection method to tackle the influence overlapping issue and shrink the size of candidate generation. Then, we propose a novel clustering-based leadership analysis to find out the opinion leader in a social network. The experimental study shows that the proposed algorithm can effectively discover the influential opinion leaders in different real datasets with efficiency and has graceful scalability.