基于Friedkin-Johnsen (FJ)模型的社交网络舆论引导机制研究
The Research of Opinion Leading Mechanisms in Social Networks Based on the Fredkin-Johnsen (FJ) Model
DOI: 10.12677/orf.2025.152125, PDF,   
作者: 鄢梓健, 张 广*:上海理工大学管理学院,上海
关键词: 舆论引导网络模型FJ模型TOPSISPublic Opinion Guidance Network Model FJ Model TOPSIS
摘要: 随着网络与通信技术的发展,如何高效引导社交网络中的舆论风向成为了一个亟待解决的问题。现有对舆论的干预手段多为简单的宏观调控,缺乏动态分析以及对个体心理等因素的考虑。对此,本文通过运用观点动力学的方法,探索社交网络的舆论引导机制。本文首先构建了包含亲密关系层、普通社交层和媒体信息层的三层网络模型。随后以观点动力学模型中的Friedkin-Johnsen (FJ)模型为基础模型,融合基于TOPSIS的干预算法,同时引入层间联动系数,构建模拟观点传播的三层网络FJ模型。然后利用上述模型进行算例仿真,通过对仿真结果进行分析以探究社交网络中的舆论传播机制及干预策略。最后,根据结果总结舆论传播规律,提炼服务于社交网络的舆论引导策略。
Abstract: With the development of network and communication technology, how to efficiently guide public opinion in social networks has become an urgent problem. Existing interventions on public opinion are mostly simple macro-control, which lacks dynamic analysis and consideration of individual psychology and other factors. In this paper, we explore the public opinion guidance mechanism of social networks by applying opinion dynamics. In this paper, we first constructed a three-layer network model including an intimate relationship layer, an ordinary social layer, and a media information layer. Subsequently, the Friedkin-Johnsen (FJ) model in the opinion dynamics model is used as the base model, and the TOPSIS-based intervention algorithm is integrated. At the same time, the inter-layer linkage coefficient is introduced to construct the FJ model of the three-layer network that simulates viewpoint propagation. Then, the above model is used to carry out an example simulation, and the simulation results are analyzed to explore the mechanism of opinion dissemination and intervention strategies in social networks. Finally, based on the results, we summarize the laws of opinion dissemination and refine the opinion guidance strategy for social networks.
文章引用:鄢梓健, 张广. 基于Friedkin-Johnsen (FJ)模型的社交网络舆论引导机制研究[J]. 运筹与模糊学, 2025, 15(2): 780-791. https://doi.org/10.12677/orf.2025.152125

参考文献

[1] 刘举胜, 何建佳, 韩景倜, 等. 观点动力学研究现状及进展述评[J]. 复杂系统与复杂性科学, 2021, 18(2): 9-20.
[2] 王龙, 田野, 杜金铭. 社会网络上的观念动力学[J]. 中国科学: 信息科学, 2018, 48(1): 3-23.
[3] 马振, 贾保先. 基于观点动力学的社交网络观点共识达成研究[J]. 中国传媒大学学报(自然科学版), 2023, 30(2): 56-67.
[4] 王龙, 伏锋, 陈小杰, 等. 复杂网络上的群体决策[J]. 智能系统学报, 2008, 3(2): 95-108.
[5] Castellano, C. (2012) Social Influence and the Dynamics of Opinions: The Approach of Statistical Physics. Managerial and Decision Economics, 33, 311-321. [Google Scholar] [CrossRef
[6] Pacheco, A.T. and Evans, T.S. (2013) Social Dynamics Models on Complex Networks. Springer-Verlag.
[7] Acemoglu, D. and Ozdaglar, A. (2010) Opinion Dynamics and Learning in Social Networks. Dynamic Games and Applications, 1, 3-49. [Google Scholar] [CrossRef
[8] 熊熙, 胡勇. 基于社交网络的观点传播动力学研究[J]. 物理学报, 2012, 61(15): 104-110.
[9] 刘琪, 肖人彬. 观点动力学视角下基于意见领袖的网络舆情反转研究[J]. 复杂系统与复杂性科学, 2019, 16(1): 1-13.
[10] 杨雷, 赵九茹. 决策偏好不确定条件下群体决策收敛一致性研究[J]. 运筹与管理, 2017, 26(1): 96-102.
[11] Zha, Q., Kou, G., Zhang, H., Liang, H., Chen, X., Li, C., et al. (2020) Opinion Dynamics in Finance and Business: A Literature Review and Research Opportunities. Financial Innovation, 6, Article No. 44. [Google Scholar] [CrossRef
[12] Friedkin, N.E. and Johnsen, E.C. (1990) Social Influence and Opinions. The Journal of Mathematical Sociology, 15, 193-206. [Google Scholar] [CrossRef
[13] 周葆华. 网络舆论过程与动态演化: 基于计算传播研究的分析[J]. 西北师大学报(社会科学版), 2019, 56(1): 37-46.
[14] 吴金闪, 狄增如. 从统计物理学看复杂网络研究[J]. 物理学进展, 2004, 24(1): 18-46.
[15] Watts, D.J. and Strogatz, S.H. (1998) Collective Dynamics of ‘Small-World’ Networks. Nature, 393, 440-442. [Google Scholar] [CrossRef] [PubMed]
[16] Barabási, A. and Albert, R. (1999) Emergence of Scaling in Random Networks. Science, 286, 509-512. [Google Scholar] [CrossRef] [PubMed]
[17] 范如国, 王奕博, 罗明, 等. 基于SEIR的新冠肺炎传播模型及拐点预测分析[J]. 电子科技大学学报, 2020, 49(3): 369-374.
[18] 周磊, 龚志强, 支蓉, 等. 基于复杂网络研究中国温度变化的区域特征[J]. 物理学报, 2009, 58(10): 7351-7358.
[19] 虞晓芬, 傅玳. 多指标综合评价方法综述[J]. 统计与决策, 2004(11): 119-121.
[20] 于会, 刘尊, 李勇军. 基于多属性决策的复杂网络节点重要性综合评价方法[J]. 物理学报, 2013, 62(2): 54-62.