Influence is an important part of social network. After the appearance of online social network, the data could be analyzed conveniently. Based on the influence of important nodes and communities in the network, a new influence modeling method which is based on twin support vector machines is proposed. Also the uncertain query technology is applied to search the key nodes. The new methods are used to analyze the data of Weibo. Firstly the fuzzy twin support vector machines are used to identify the communities, and the different kinds of influence are calculated by the uncertain query method. Compared with the common optimization algorithm, the computational results show that the new algorithm can effectively know the influence of the online social network and the uncertain query technology can be used smoothly.
展开▼
