基于多智能体强化学习的社交网络舆情增强一致性方法

谢光强; 许浩然; 李杨; 陈广福

doi:10.12052/gdutxb.220042

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于多智能体强化学习的社交网络舆情增强一致性方法

综合研究 | 更新时间：2026-05-27

- 基于多智能体强化学习的社交网络舆情增强一致性方法
- Consensus Opinion Enhancement in Social Network with Multi-agent Reinforcement Learning
- 广东工业大学学报 2022年39卷第6期页码：36-43
- 作者机构：
  
  广东工业大学计算机学院,广东,广州,510006
- 作者简介：
  
  谢光强(1979–) ，男，教授，博士，主要研究方向为多智能体、智能控制、差分隐私保护
  李杨(1980–) ，女，教授，博士，主要研究方向为多智能体、差分隐私保护，E-mail：liyang@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(61972102)
- DOI：10.12052/gdutxb.220042
  中图分类号： TP391
- 网络首发：2022-11-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
谢光强, 许浩然, 李杨, 陈广福. 基于多智能体强化学习的社交网络舆情增强一致性方法[J]. 广东工业大学学报, 2022, 39(6): 36-43.

Xie Guang-qiang, Xu Hao-ran, Li Yang, et al. Consensus Opinion Enhancement in Social Network with Multi-agent Reinforcement Learning[J]. 2022, 39(6): 36-43.
谢光强, 许浩然, 李杨, 陈广福. 基于多智能体强化学习的社交网络舆情增强一致性方法[J]. 广东工业大学学报, 2022, 39(6): 36-43. DOI： 10.12052/gdutxb.220042.

Xie Guang-qiang, Xu Hao-ran, Li Yang, et al. Consensus Opinion Enhancement in Social Network with Multi-agent Reinforcement Learning[J]. 2022, 39(6): 36-43. DOI： 10.12052/gdutxb.220042.

摘要

针对社交网络舆情动力学的增强一致性问题，提出了一种基于多智能体强化学习的智能感知模型(Consensus Opinion Enhancement with Intelligent Perception

COEIP) 。在舆情动力学场景下的马尔科夫决策过程中，首先通过双向循环神经网络设计了智能体的决策模型以解决智能体不定长感知的问题。然后通过差分奖励的思想针对收敛效率、连通度和通信代价三类目标，设计了有效的奖励函数。最后为优化COEIP模型，设计了基于策略梯度的多智能体探索与更新算法，让智能体在彼此交互过程中，通过奖励值自适应学习具备多目标权衡能力的邻域选择策略。大量仿真验证了COEIP在社交网络舆情动力学场景下可以有效调和智能体间的矛盾，降低系统稳定时的簇数，进而增强系统的舆情一致性。本模型为大规模社交网络下提高人群意见的统一性提供了新的解决方案，具有重要的理论指导意义。

Abstract

Aiming at the problem of consensus enhancement in opinion dynamics of social network

a consensus opinion enhancement with intelligent perception (COEIP) model based on multi-agent reinforcement learning is proposed. In the Markov decision-making process in opinion dynamics

firstly

the decision-making model of agent is designed through bidirectional recurrent neural network to solve the problem of uncertain-length perception. Then

through the idea of difference reward

an effective reward function is designed for the three objectives of convergence efficiency

connectivity and communication cost. Finally

in order to optimize COEIP model

a multi-agent exploration and collaborative update algorithm based on policy gradient is designed

which can enable agents to adaptively learn the neighborhood selection strategy with multi-objective trade-off ability through the reward value in the process of interaction with each other. A large number of simulations verify that COEIP can effectively reconcile the contradictions between agents and reduce the number of clusters when the system is stable in the scenario of opinion dynamics of social network

thus enhancing the consensus opinion of the system. This model provides a new solution for improving the unity of people's opinions under large-scale social networks

which has important theoretical guiding significance.

关键词

Keywords

references

DONG Y C, ZHA Q B, ZHANG H J, et al . Consensus reaching in social network group decision making: research paradigms and challenges [J ] . Knowledge-Based Systems, 2018, 162: 3-13.

ZHANG Z, GAO Y, LI Z L. Consensus reaching for social network group decision making by considering leadership and bounded confidence [J]. Knowledge-Based Systems, 2020, 204: 106240.

SCOTT J, CARRINGTON P J. The SAGE handbook of social network analysis[M]. California: SAGE Publications, 2011.

LI Y H, KOU G, LI G X, et al . Multi-attribute group decision making with opinion dynamics based on social trust network [J ] . Information Fusion, 2021, 75: 102-115.

LI T Y, ZHU H M. Effect of the media on the opinion dynamics in online social networks [J]. Physica A:Statistical Mechanics and its Applications, 2020, 551: 124117.

JIAO Y R, LI Y L. An active opinion dynamics model: the gap between the voting result and group opinion [J]. Information Fusion, 2021, 65: 128-146.

DOUVEN I, HEGSELMANN R. Mis-and disinformation in a bounded confidence model [J]. Artificial Intelligence, 2021, 291: 103415.

BISWAS K, BISWAS S, SEN P. Block size dependence of coarse graining in discrete opinion dynamics model: application to the US presidential elections [J]. Physica A:Statistical Mechanics and its Applications, 2021, 566: 125639.

ZHU L X, HE Y L, ZHOU D Y. Neural opinion dynamics model for the prediction of user-level stance dynamics [J]. Information Processing Management, 2020, 57(2): 102031.

BRAVO-MARQUEZ F, GAYO-AVELLO D, MENDOZA M, et al . Opinion dynamics of elections in Twitter[C ] //2012 Eighth Latin American Web Congress. Colombia: IEEE, 2012: 32-39.

ZHA Q B, KOU G, ZHANG H J, et al . Opinion dynamics in finance and business: a literature review and research opportunities [J ] . Financial Innovation, 2020, 6(1): 1-22.

DONG Y C, ZHAN M, KOU G, et al . A survey on the fusion process in opinion dynamics [J ] . Information Fusion, 2018, 43: 57-65.

SRBU A, LORETO V, SERVEDIO V D P, et al . Opinion dynamics: models, extensions and external effects[M ] //Participatory sensing, opinions and collective awareness. Berlin: Springer, 2017: 363-401.

URENA R, CHICLANA F, MELANCON G, et al . A social network based approach for consensus achievement in multiperson decision making [J ] . Information Fusion, 2019, 47: 72-87.

CABRERIZO F J, AL-HMOUZ R, MORFEQ A, et al . Soft consensus measures in group decision making using unbalanced fuzzy linguistic information [J ] . Soft Computing, 2017, 21(11): 3037-3050.

LI G X, KOU G, PENG Y. Heterogeneous large-scale group decision making using fuzzy cluster analysis and its application to emergency response plan selection [J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2021, 52(6): 3391-3403.

XU S, WANG P, LYU J. Iterative neighbour-information gathering for ranking nodes in complex networks [J]. Scientific reports, 2017, 7(1): 1-13.

NEDIĆ A, OLSHEVSKY A, RABBAT M G. Network topology and communication-computation tradeoffs in decentralized optimization [J]. Proceedings of the IEEE, 2018, 106(5): 953-976.

ZHANG K Q, YANG Z R, BAŞAR T. Multi-agent reinforcement learning: a selective overview of theories and algorithms [J]. Handbook of Reinforcement Learning and Control, 2021: 321-384.

ZHENG S Y, CUI M, ZHANG G C. Reinforcement learning-based online trajectory optimization for secure UAV communications [J]. Journal of Guangdong University of Technology, 2021, 38(04): 59-64.

SHOU Z Y, DI X. Reward design for driver repositioning using multi-agent reinforcement learning [J]. Transportation research part C:emerging technologies, 2020, 119: 102738.

SUN X Z, QIU J. Two-stage volt/var control in active distribution networks with multi-agent deep reinforcement learning method [J]. IEEE Transactions on Smart Grid, 2021, 12(4): 2903-2912.

ZHANG K Q, YANG Z R, LIU H, et al . Fully decentralized multi-agent reinforcement learning with networked agents[C ] //International Conference on Machine Learning. Sweden: IMLS, 2018: 5872-5881.

DEY R, SALEM F M. Gate-variants of gated recurrent unit (GRU) neural networks[C]//2017 IEEE 60th international midwest symposium on circuits and systems. Michigan: IEEE, 2017: 1597-1600.

SILVER D, SINGH S, PRECUP D, et al . Reward is enough [J ] . Artificial Intelligence, 2021, 299: 103535.

SUTTON R S, BARTO A G. Reinforcement learning: an introduction[M]. Massachusetts: MIT press, 2018.

FOERSTER J, FARQUHAR G, AFOURAS T, et al . Counterfactual multi-agent policy gradients[C ] //Proceedings of the AAAI conference on artificial intelligence. Louisiana: AAAI Press, 2018, 32(1) : 2974-2982.

AGOGINO A, TURNER K. Multi-agent reward analysis for learning in noisy domains[C]//Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems. Utrecht: IFAAMAS, 2005: 81-88.

BARRAT A, BARTHELEMY M, PASTOR-SATORRAS R, et al . The architecture of complex weighted networks [J ] . Proceedings of the national academy of sciences, 2004, 101(11): 3747-3752.

SILVER D, LEVER G, HEESS N, et al . Deterministic policy gradient algorithms[C ] //International conference on machine learning. Beijing: IMLS, 2014: 387-395.

BLONDEL V D, HENDRICKX J M, TSITSIKLIS J N. On Krause's multi-agent consensus model with state-dependent connectivity [J]. IEEE transactions on Automatic Control, 2009, 54(11): 2586-2597.

WU C W. Algebraic connectivity of directed graphs [J]. Linear and multilinear algebra, 2005, 53(3): 203-223.

ESFAHANIAN A H. Connectivity algorithms[M]//Topics in structural graph theory. Cambridge: Cambridge University Press, 2013: 268-281.

WANG H J, SHANG L H. Opinion dynamics in networks with common-neighbors-based connections [J]. Physica A:Statistical Mechanics and its Applications, 2015, 421: 180-186.

CHENG C, YU C B. Opinion dynamics with bounded confidence and group pressure [J]. Physica A:Statistical Mechanics and its Applications, 2019, 532: 121900.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

编码−解码方案与参量Lyapunov方法下多智能体系统的拟一致性

基于脉冲观测器的多智能体系统的领导跟随一致性

动态事件触发脉冲机制下多智能体系统的拟一致性

FDI攻击下非线性多智能体系统分布式无模型自适应控制

两种不同脉冲欺骗攻击下随机多智能体系统的均方拟一致性