[1]CHEN Bolun,ZHU Guochang,JI Min,et al.Negative influence propagation suppression method based on a random walk under cost constraint[J].CAAI Transactions on Intelligent Systems,2022,17(2):266-275.[doi:10.11992/tis.202101037]
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
17
Number of periods:
2022 2
Page number:
266-275
Column:
学术论文—机器学习
Public date:
2022-03-05
- Title:
-
Negative influence propagation suppression method based on a random walk under cost constraint
- Author(s):
-
CHEN Bolun; ZHU Guochang; JI Min; ZHU Hongfei; WEI Cheng
-
Institute of Computer and Software Engineering, Huaiyin Institute of Technology, Huai’an 223003, China
-
- Keywords:
-
social network; cost constraint; information diffusion; superposed random walk; negative influence; propagation inhibition; percolation; sub-graph
- CLC:
-
TP301.6
- DOI:
-
10.11992/tis.202101037
- Abstract:
-
The information diffusion mechanism of social networking among different users is often affected by the influence among users, so it is particularly necessary to carry out a complex network analysis. In this paper, we first study the influence propagation model of complex networks with cost constraints. In the case of the unknown network propagation principle, we use a superposed random walk strategy to measure the influence propagation of networks, control the scope of influence propagation in a certain sub-graph, and design an effective method to suppress negative influence propagation. On this basis, the idea of percolation is introduced to determine the set size of restraining nodes. Experimental results show that this algorithm can effectively limit the propagation of negative influence and achieve better performance under cost constraints. This paper is of great theoretical significance to analyzing, understanding, and predicting social network’s topological structure, function, and dynamic behavior. It plays an important role in public opinion control and false information suppression.