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

doi:10.3778/j.issn.1002-8331.2310-0208

Abstract

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

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

CUI Xuelian, DONG Haitao. Research on Social Network Public Opinion Control Strategy Based on Key Node Identification[J]. Computer Engineering and Applications, 2024, 60(20): 262-273.

崔雪莲, 董海涛. 基于关键节点识别的社交网络舆情控制策略研究[J]. 计算机工程与应用, 2024, 60(20): 262-273.

References

[1] 汪亭亭, 梁宗文, 张若曦. 基于信息熵与迭代因子的复杂网络节点重要性评价方法[J]. 物理学报, 2023, 72(4): 337-347.
WANG T T, LIANG Z W, ZHANG R X. Importance evaluation method of complex network nodes based on information entropyand iteration factor[J]. Acta Physica Sinica, 2023, 72(4): 337-347.
[2] 侯艳辉, 孟帆, 王家坤, 等. 后真相时代考虑信息熵的网民观点演化与舆情研判引导研究[J]. 情报杂志, 2022, 41(7): 116-123.
HOU Y H, MENG F, WANG J K, et al. Evolution of netizens opinions, publics judgment and guidance in the post-truth era considering information entropy[J]. Journal of Intelligence, 2022, 41(7): 116-123.
[3] 魏莹, 刘冠, 李锋. 线上社交网络上信息扩散中“隐形”关键节点的识别及影响力评价[J]. 情报科学, 2018, 36(3): 138-143.
WEI Y, LIU G, LI F. Recognizing and influence evaluating of the “lurkers” in information diffusion on social network platform[J]. Information Science, 2018, 36(3): 138-143.
[4] 顾洁, 王筱纶, 胡安安. 社交网络信息竞争扩散的关键节点策略研究[J]. 情报科学, 2020, 38(3): 78-86.
GU J, WANG X L, HU A A. Seeding strategy of competitive diffusion in social network[J]. Information Science, 2020, 38(3): 78-86.
[5] 魏莹, 李锋. 基于主路径分析的关键节点识别与谣言扩散抑制研究[J]. 情报科学, 2018, 36(6): 13-19.
WEI Y, LI F. The study of key nodes identification for restraining rumor propagation based on main path analysis[J]. Information Science, 2018, 36(6): 13-19.
[6] 蒋侃, 唐竹发, 隋浩. 基于微博信息扩散质量的网络舆情关键节点识别[J]. 情报科学, 2016, 34(7): 64-69.
JIANG K, TANG Z F, SUI H. Research on identifing key nodes of network public opinion based on the quality of micro-blog information diffusion[J]. Information Science, 2016, 34(7): 64-69.
[7] 王曰芬, 王一山, 杨洁. 基于社区发现和关键节点识别的网络舆情主题发现与实证分析[J]. 图书与情报, 2020(5): 48-58.
WANG Y F, WANG Y S, YANG J. Topic discovery and empirical analysis of network public opinion based on community detection and key node identification[J]. Library & Information, 2020(5): 48-58.
[8] 汪小帆, 李翔, 陈关荣. 网络科学导论[M]. 北京: 高等教育出版社, 2012.
WANG X F, LI X, CHEN G R. Network science an introduction[M]. Beijing: Higher Education Press, 2012.
[9] 席耀一, 高鑫, 王小明, 等. 基于ETM模型的中亚国家“一带一路”网络舆情热点监测[J]. 情报杂志, 2020, 39(11): 82-89.
Ⅺ Y Y, GAO X, WANG X M, et al. Detection of hot spots of “belt and road” network public opinion in central Asian countries based on ETM model[J]. Journal of Intelligence, 2020, 39(11): 82-89.
[10] KITSAK M, GALLOS L K, HAVLIN S. Identification of influential spreaders in complex networks[J]. Nature Physics, 2010, 6(11): 888-893.
[11] ZENG A, ZHANG C. Ranking spreaders by decomposing complex networks[J]. Physics Letters A, 2013, 377(14): 1031-1035.
[12] CHEN D, LU L, SHANG M. Identifying influential nodes in complex networks[J]. Physica A: Statistical Mechanics and Its Applications, 2012, 391(4): 1777-1787.
[13] 姚月娇, 刘向, 余博文. 弱连接视角下的高影响力节点识别[J]. 现代情报, 2022, 42(9): 58-67.
YAO Y J, LIU X, YU B W. High-influence node recognition from the perspective of weak ties[J]. Journal of Modern Information, 2022, 42(9): 58-67.
[14] YU E, WANG Y, FU Yl. Identifying critical nodes in complex networks via graph convolutional networks[J]. Knowledge-Based Systems, 2020, 198: 105893.
[15] WANDELT S, SHI X , SUN X . Complex network metrics: can deep learning keep up with tailor-made reference algorithms?[J]. IEEE Access?, 2020, 8: 68114-68123.
[16] BONACICH P. Factoring and weighting approaches to status scores and clique identification[J]. Journal of Mathematical Sociology, 1972, 2(1): 113-120.
[17] 刘迪, 张会来. 网络舆情治理中意见领袖舆论引导的研究热点和前沿探析[J]. 现代情报, 2020, 40(9): 144-155.
LIU D, ZHANG H L. Research hotspots and frontier analysis of opinion leaders public opinion guidance in the governance of network public opinion[J]. Journal of Modern Information, 2020, 40(9): 144-155.
[18] 胡钢, 卢志宇, 王乐萌, 等. 基于复杂网络多阶邻域贡献度的节点重要性序结构辨识[J]. 电子学报, 2023, 51(7): 1957-1963.
HU G, LU Z Y, WANG L M, et al. Identification of node importance order structure based on multi-order neighborhood contribution of complex network[J]. Acta Electronica Sinica, 2023, 51(7): 1957-1963.
[19] 庄文英, 许英姿, 任俊玲, 等. 突发事件舆情演化与治理研究--基于拓展多意见竞争演化模型[J]. 情报杂志, 2021, 40(12): 127-134.
ZHUANG W Y, XU Y Z, REN J L, et al. Research on the evolution and governance of public opinion on emergencies-based on expanded SEInR model[J]. Journal of Intelligence, 2021, 40(12): 127-134.
[20] 阮逸润, 老松杨, 汤俊, 等. 基于引力方法的复杂网络节点重要度评估方法[J]. 物理学报, 2022, 71(17): 298-309.
RUAN Y R, LAO S Y, TANG J, et al. Node importance ranking method in complex network based on gravity method[J]. Acta Physica Sinica, 2022, 71(17): 298-309.
[21] 吴亚丽, 任远光, 董昂, 等. 基于邻域K-shell分布的关键节点识别方法[J]. 计算机工程与应用, 2024, 60(2): 87-95.
WU Y L, REN Y G, DONG A, et al. Key nodes identification method based on neighborhood K-shell distribution[J]. Computer Engineering and Applications, 2024, 60(2): 87-95.
[22] 钟磊, 宋香荣, 孙瑞娜. 基于LeaderRank的意见领袖发现模型及其应用[J]. 情报杂志, 2021, 40(4): 194-199.
ZHONG L, SONG X R, SUN R N. Opinion leader discovery model based on LeaderRank and its application[J]. Journal of Intelligence, 2021, 40(4): 194-199.
[23] 王环, 朱敏. 基于点权的混合K-shell关键节点识别方法[J]. 华东师范大学学报 (自然科学版), 2019(3): 101-109.
WANG H, ZHU M. Vital nodes identification by the hybrid K-shell method based on vertex strength[J]. Journal of East China Normal University (Natural Science), 2019(3): 101-109.
[24] 熊才权, 古小惠, 吴歆韵. 基于K-shell位置和两阶邻居的复杂网络节点重要性评估方法[J]. 计算机应用研究, 2023, 40(3): 738-742.
XIONG C Q, GU X H, WU X Y. Evaluation method of node importance in complex networks based on K-shell position and neighborhood within two steps[J]. Application Research of Computers, 2023, 40(3): 738-742.
[25] FREEMAN L C. A set of measures of centrality based on betweenness[J]. Sociometry, 1977, 40(1): 35-41.
[26] LATORA V, MARCHIORI M. Efficient behavior of small-world networks[J]. Physical Review Letters, 2001, 87(19): 198701.
[27] BURT R S. Structural holes: the social structure of competition[M]. Cambridge: Harvard University Press, 2009.
[28] 苏晓萍, 宋玉蓉. 利用邻域“结构洞”寻找社会网络中最具影响力节点[J]. 物理学报, 2015, 64(2): 5-15.
SU X P, SONG Y R. Leveraging neighborhood “structural holes” to identifying key spreaders in social networks[J]. Acta Physica Sinica, 2015, 64(2): 5-15.
[29] RUAN Y, LAO S, XIAO Y. Identifying influence of nodes in complex networks with coreness centrality: decreasing the impact of densely local connection[J]. Chinese Physics Letters, 2016, 33(2): 028901.
[30] 李钢, 王聿达, 崔蓉. KiC: 一种结合“结构洞” 约束值与K壳分解的社交网络关键节点识别算法[J]. 现代情报, 2020, 40(12): 27-32.
LI G, WANG Y D, CUI R. KiC: an extended k-shell decomposition based on improved network constraint coefficient[J]. Journal of Modern Information, 2020, 40(12): 27-32.
[31] WANG M, LI W C, GUO Y N, et al. Identifying influential spreaders in complex networks based on improved k-shell method[J]. Physical A, 2020, 554: 124229.
[32] XU X, ZHU C, WANG Q. Identifying critical nodes in complex networks via graph convolutional networks[J]. Knowledge-Based Systems, 2020, 198: 105893.
[33] 杨松青, 蒋沅, 童天驰, 等. 基于Tsallis熵的复杂网络节点重要性评估方法[J]. 物理学报, 2021, 70(21): 267-278.
YANG S Q, JIANG R, TONG T C. A method for evaluating the importance of nodes in complex network based on Tsallis entropy[J]. Acta Physica Sinica, 2021, 70(21): 267-278.
[34] 陈俊华, 边宅安, 李佳慧, 等. 基于相对熵的节点影响力测量方法[J]. 计算机科学, 2018, 45(11): 292-298.
CHEN J H, BIAN Z A, LI J H, et al. Measuring method of node influence based on relative entropy[J]. Computer Science, 2018, 45(11): 292-298.
[35] 周丽娜, 常笑, 胡枫. 利用邻接结构熵确定超网络关键节点[J]. 计算机工程与应用, 2022, 58(8): 76-82.
ZHOU L N, CHANG X, HU F. Using adjacent structure entropy to determine vital nodes of hypernetwork[J]. Computer Engineering and Applications, 2022, 58(8): 76-82.
[36] 龚志豪, 蒋沅, 代冀阳, 等. 基于交叉熵的节点重要性排序算法[J]. 电子科技大学学报, 2023, 52(6): 945-953.
GONG Z H, JIANG R, DAI J Y, et al. Node importance ranking algorithm based on cross entropy[J]. Journal of University of Electronic Science and Technology of China, 2023, 52(6): 945-953.
[37] 胡钢, 徐翔, 高浩. 基于邻接信息熵的网络节点重要性识别算法[J]. 系统工程理论与实践, 2018, 40(3): 715-723.
HU G, XU X, GAO H. Node importance recognition algorithm based on adjacency information entropy in networks[J]. Systems Engineering-Theory & Practice, 2018, 40(3): 715-723.
[38] 胡钢, 牛琼, 许丽鹏, 等. 基于网络超链接信息熵的节点重要性序结构演化建模分析[J]. 电子学报, 2022, 50(11): 2638-2644.
HU G, NIU Q, XU L P. The model to analyses of node importance order structure evolution based on network hyperlink information entropy[J]. Acta Electronica Sinica, 2022, 50(11): 2638-2644.
[39] 洪成, 蒋沅, 严玉为, 等. 基于层间邻域信息熵的时序网络节点重要性评估方法[J]. 复杂系统与复杂性科学, 2024, 21(1): 20-27.
HONG C, JIANG R, YAN Y W. A method of evaluating importance of nodes in temporal network based on inter-layer neighborhood information entropy[J]. Complex Systems and Complexity Science, 2024, 21(1): 20-27.
[40] 聂琦, 张鸫, 江昊. 基于情绪信息熵的网络舆情传播模型研究[J]. 武汉大学学报 (工学版), 2022, 55(7): 725-731.
NIE Q, ZHANG D, JIANG H. Research on internet public opinion transmission model with emotional information entropy[J]. Engineering Journal of Wuhan University, 2022, 55(7): 725-731.
[41] 郭程远, 陈鸿昶, 王庚润, 等. 基于迭代K-shell和改进信息熵的节点重要性排序算法[J]. 信息工程大学学报, 2022, 23(5): 556-562.
GUO C Y, CHEN H C, WANG G R, et al. Node importance ranking algorithm based on iterative k-shell and improved information entropy[J]. Journal of Information Engineering University, 2022, 23(5): 556-562.
[42] ZACHARY W W. An information flow model for conflict and fission in small groups1[J]. Journal of Anthropological Research, 1976, 33(4): 452-473.
[43] LUSSEAU D, SCHNEISER K, BOISSEAU O. The bottlenose dolphin community of doubtful sound features a large proportion of long-lasting associations[J]. Behavioral Ecology and Sociobiology, 2003, 54(4) : 396-405.
[44] GIRVAN M, NEWMAN M E. Community structure in social and biological networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2002, 99 (12): 7821-7826.
[45] NEWMAN M E. Finding community structure in networks using the eigenvectors of matrices[J]. Physical Review E, 2006, 74 (3): 036104.