计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (20): 262-273.DOI: 10.3778/j.issn.1002-8331.2310-0208

• 网络、通信与安全 • 上一篇    下一篇

基于关键节点识别的社交网络舆情控制策略研究

崔雪莲,董海涛   

  1. 山东科技大学 经济管理学院,山东 青岛 266590
  • 出版日期:2024-10-15 发布日期:2024-10-15

Research on Social Network Public Opinion Control Strategy Based on Key Node Identification

CUI Xuelian, DONG Haitao   

  1. School of Economics and Management, Shandong University of Science and Technology, Qingdao, Shandong 266590, China
  • Online:2024-10-15 Published:2024-10-15

摘要: 有效识别社交网络中的关键节点,在舆情的控制和引导方面起到重要作用。针对社交网络舆情传播问题,提出一种基于关键节点识别的控制方法。设计了基于双指标香农熵的关键节点识别方法,综合考虑节点在全局网络和局部网络拓扑结构中的重要性,以介数和结构洞约束系数指标作为信息函数构造节点分布概率,进而计算节点信息熵,依据信息熵大小识别舆情传播中的关键节点。通过仿真实验验证关键节点识别方法的有效性,并基于SIR模型分析所识别的关键节点在舆情传播中的作用,最后给出控制策略。实验结果表明,除了网络中心节点外,该方法能有效识别网络中的“桥”节点,在舆情传播仿真中,增加控制桥节点后舆情传播速度和范围明显降低,且选择关键节点数在2%~3%范围内舆情控制效用最优,超过该范围边际效用明显减少。

关键词: 社交网络, 舆情传播, 关键节点, 信息熵

Abstract: Effective identification of key nodes in social networks plays an important role in the control and guidance of public opinion. Aiming at the problem of social network public opinion dissemination, a control method based on key node identification is proposed. Firstly, a key node identification method based on dual index Shannon entropy is designed. Considering the importance of nodes in the global network and local network topology, the intermediate number and structural hole constraint coefficient index are used as the information function to construct the node distribution probability, and then the node information entropy is calculated to identify the key nodes in the public opinion dissemination according to the size of the information entropy. Secondly, the effectiveness of the key node identification method is verified through simulation experiments, and the role of the identified key nodes in the public opinion communication is analyzed based on the SIR model. Finally, the control strategy is given. The experimental results show that this method can effectively identify the “bridge” node in the network except the network center node. In the public opinion propagation simulation, the speed and range of public opinion propagation are significantly reduced after adding the control bridge node, and the public opinion control effect is optimal when the number of key nodes is within the range of 2%~3%, and the marginal utility beyond this range is significantly reduced.

Key words: social networks, public opinion dissemination, key nodes, Shannon entropy