Dynamic Opinion Maximization Framework With Hybrid Method in Social Networks

Abstract

Dynamic Opinion Maximization (DOM) is an optimization issue, which determines some influential network nodes (i.e., seed nodes) to propagate specific opinions towards a certain object (e.g., one individual) using a dynamic opinion model, and achieve the optimal opinion propagation. In this paper, we study the DOM and construct an effective hybrid framework to address the problem. Firstly, we explicate the DOM problem and design the objective function of the DOM. Then, based on the activation status with the linear threshold model and the dynamic opinion process with the weighted Hegselmann-Krause model, we devise the activated opinion model to estimate the activation status and dynamic opinion process of activated nodes effectively. We propose an effective hybrid framework to select the seed nodes, which includes community detection, the determination of candidate seed nodes, and the seeding algorithm with discrete particle swarm optimization. In particular, to better generate the seed nodes and promote their propagation, we design the selection algorithm of candidate seed nodes and replacement strategy. Experimental results show the superiority of the proposed hybrid framework on the average opinions and the number of activated nodes than the baseline algorithms. Our method gains 17.89% more average opinions than EPN, 14.57% than RIS, 20.19% than CIDM, 2.58% than ATOM, and 7.22% than CELF on the eight social network datasets. Moreover, our method gains 28.17% more activated nodes than EPN, 25.31% than RIS, 36.34% than CIDM, 16.82% than ATOM, and 19.68% than CELF on average.