A study on the influence propagation model in topic attention networks

The social networks with the complex user relations and huge amount of data and hidden information, bring new opportunities and challenges for the study of information diffusion and influence maximization. In recent years, there are more and more researches on the influence maximization of topic preference. However, most of the existing researches only take the topic as an attribute of the users, and the importance of the topic in network structure is not considered. In view of this situation, firstly, this paper constructed a new topic attention network model fusing the social relation and the topic preference. Secondly, based on connected degree of set pair and Markov random walk model, we propose the calculated method of the topic preference for users, and then mining the seed set with influence by the greedy strategy. Thirdly, we propose the calculated method of the activation probability of the user based on the user relation and the topic preference, and propose the influence maximization algorithm TAN-CELF in topic attention networks. Finally, on Dou-ban network dataset, from three metrics ISST, ISRT and ISRNT, compare with algorithm L-GAUP and CELF, the experimental results show that algorithm TAN-CELF that is proposed by this paper has a higher performance on influence scope. © 2017 Totem Publisher, Inc. All rights reserved.