Research on the Interaction Characteristics of Social Bots in the Echo Chamber Effect of Public Opinion Dissemination Under Major Emergencies

Wang Xiwei; Zhao Yang; Tang Ming

doi:10.13266/j.issn.0252-3116.2026.03.007

2026 , Vol. 70 >Issue 3: 73 - 87

DOI: https://doi.org/10.13266/j.issn.0252-3116.2026.03.007

RESEARCH PAPERS

Research on the Interaction Characteristics of Social Bots in the Echo Chamber Effect of Public Opinion Dissemination Under Major Emergencies

Wang Xiwei ,
Zhao Yang ,
Tang Ming

Expand

1 School of Business and Management, Jilin University, Changchun 130012;
2 Research Center for Big Data Management, Jilin University, Changchun 130012;
3 Research Center of Cyberspace Governance, Jilin University, Changchun 130012;
4 Institute of National Development and Security Research, Jilin University, Changchun 130012;
5 Faculty of Humanities and Social Sciences, City University of Macau, Macau 999078

Received date: 2024-12-19

Revised date: 2025-04-06

Online published: 2026-02-09

Supported by

This work is supported by the project of Humanities and Social Sciences of the Ministry of Education, titled “Research on Human-Computer Interaction Risks and Governance Paths of Artificial Intelligence Generated Content under the Perspective of Information Ecology” (Grant No. 24A10183005).

Fold

Abstract

[Purpose/Significance] The study of social bots interaction characteristics in public opinion dissemination under major emergencies is of great significance for improving public opinion guidance under future emergencies, realizing public emergency response measures and building a modernized national governance system. [Method/Process] Based on social network theory, this study constructed an identification model of social bots interaction characteristics in the echo chamber effect of public opinion dissemination using BERTopic topic model and social network analysis methods. Two public opinion events, the Meizhou highway collapse and the Guangzhou tornado, were analyzed empirically to identify the echo chamber effect and its social bots, and to analyze the interaction characteristics of social bots in the echo chamber effect from the perspectives of content and behavior. [Result/Conclusion] In terms of content characteristics, the echo chamber effect and social bots affect more negative human emotions, and the social bots in the echo chamber effect focus on monotonous topics and are highly homogenized. In terms of behavioral characteristics, social bots communicate with humans more through information forwarding behaviors to promote the echo chamber effect; the ability of social bots to improve the efficiency of network information dissemination is lower than that of humans, and social bots are at the endpoint position of the echo chamber network. It is demonstrated that the identification model proposed in this paper performs better in terms of robustness, fault tolerance and generalization ability compared to other social robot identification models.

Key words： major emergencies; opinion dissemination; echo chamber effect; social bots; interaction characteristics

Cite this article

Wang Xiwei , Zhao Yang , Tang Ming . Research on the Interaction Characteristics of Social Bots in the Echo Chamber Effect of Public Opinion Dissemination Under Major Emergencies[J]. Library and Information Service, 2026 , 70(3) : 73 -87 . DOI: 10.13266/j.issn.0252-3116.2026.03.007

References

[1] 中华人民共和国应急管理部门. 2024年全国自然灾害基本情况[EB/OL]. [2025-04-04]. https://www.mem.gov.cn/xw/yjglbgzdt/202501/t20250117_516032.shtml. (Ministry of Emergency Management of the People’s Republic of China. Overview of national natural disasters in 2024[EB/OL]. [2025-04-04]. https://www.mem.gov.cn/xw/yjglbgzdt/202501/t20250117_516032.shtml.)
[2] 中华人民共和国中央人民政府. 中共中央国务院印发《国家突发事件总体应急预案》[EB/OL]. [2025-04-04]. https://www.gov.cn/zhengce/202502/content_7005635.htm. (Government of the People’s Republic of China. The Central Committee of the Communist Party of China and the State Council issued the general emergency response plan for national emergencies. [EB/OL]. [2025-04-04]. https://www.gov.cn/zhengce/202502/content_7005635.htm.)
[3] YAN Z, ZHOU X,REN J,et al. Identifying underlying influential factors in information diffusion process on social media platform: a hybrid approach of data mining and time series regression[J]. Information processing & management, 2023, 60(5): 103438.
[4] 王晰巍, 庄蕙荥, 姜奕冰, 等. 重大突发事件下网络舆情传播中回声室网络结构研究[J]. 情报理论与实践, 2024, 47(1): 101-109. (WANG X W, ZHUANG H Y, JIANG Y B, et al. Research on network structure of echo chamber in network public opinion propagation for major emergencies[J]. Information studies: theory & application, 2024, 47(1): 101-109.)
[5] DWIVEDI Y K, KSHETRI N, HUGHES L, et al. “So what if ChatGPT wrote it?” multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy[J]. Information journal of information management, 2023, 71: 102642.
[6] 巩雪, 蔡萌, 杨茗, 等. 社交机器人在新兴科学技术传播中的情绪化舆情引导研究[J]. 情报理论与实践, 2025, 48(2): 113-123. (GONG X, CAI M, YANG M, et al. Emotional public opinion guidance by social bots in the communication of emerging science and technology[J]. Information studies: theory & application, 2025, 48(2): 113-123.)
[7] LUO H, MENG X, ZHAO Y F, et al. Rise of social bots: the impact of social bots on public opinion dynamics in public health emergencies from an information ecology perspective[J]. Telematics and informatics, 2023, 85: 102051.
[8] CHEN W, PACHECO D, YANG K, et al. Neutral bots probe political bias on social media[J]. Nature communications, 2022, 13(1): 5580.
[9] NGUYEN H D, NGUYEN D Q, NGUYEN C D, et al. Supervised learning models for social bot detection: literature review and benchmark[J]. Expert systems with applications, 2024, 238: 122217.
[10] HUANG H T, TIAN H, ZHENG X L, et al. CGNN: a compatibility-aware graph neural network for social media bot detection[J]. IEEE transactions on computational social systems, 2024, 11(5): 6528-6543.
[11] PEDERSEN M Y, SLAVKOVIK M, SMETS S. Detecting bots with temporal logic[J]. Synthese, 2023, 202(3): 79.
[12] CAI M, LUO H, MENG X, et al. Network distribution and sentiment interaction: information diffusion mechanisms between social bots and human users on social media[J]. Information processing & management, 2023, 60(2): 103197.
[13] 许灵毓, 钟义信, 陈志成. 社交机器人对社会舆论的影响因素研究[J]. 智能系统学报, 2024, 19(1): 122-131. (XU L Y, ZHONG Y X, CHEN Z C. Research on the influence factors of social robots on social opinions[J]. CAAI transactions on intelligent systems, 2024, 19(1): 122-131.)
[14] NG LHX, CARLEY KM. Deflating the Chinese balloon: types of Twitter bots in US-China balloon incident[J]. Epj data science, 2023, 12(1): 63.
[15] 申琦, 王璐瑜. 当“机器人”成为社会行动者:人机交互关系中的刻板印象[J]. 新闻与传播研究, 2021, 28(2): 37-52,127. (SHEN Q, WANG L Y. When robots become social actors: stereotypes in human-robot interaction[J]. Journalism & communication, 2021, 28(2): 37-52,127.)
[16] ALRHMOUN A, KERTES J. Emergent local structures in an ecosystem of social bots and humans on Twitter[J]. Epj data science, 2023. 12(1): 39.
[17] DELKHOSH F, GOPAL RD, PATTERSON RA, et al. Impact of bot involvement in an incentivized blockchain-based online social media platform[J]. Journal of management information systems, 2023, 40(3): 778-806.
[18] SUNSTEIN CR. Infotopia: how many minds produce knowledge[M]. Oxford: Oxford University Press, 2006.
[19] 姜婷婷, 许艳闰. 窄化的信息世界: 国外信息茧房、选择性接触与回音室研究进展[J]. 图书情报知识, 2021, 38(5): 134-144. (JIANG T T, XU Y R. Narrowed information universe: a review of research on information cocoons, selective exposure, and echo chambers[J]. Documentation, information & knowledge, 2021, 38(5): 134-144.)
[20] 乌吉斯古楞, 王晰巍, 王楠阿雪. 智能推荐算法作用下重大突发事件群体信息从众行为研究——基于社会学习理论视角[J]. 图书情报工作, 2024, 68(20): 87-103. (WUJI S, WANG X W, WANG N A X. Research on group information herd behavior in major emergent events under the influence of intelligent recommendation algorithms: a social learning theory perspective[J]. Library and information service, 2024, 68(20): 87-103.)
[21] REN Z C, SHEN Q, DIAO X L, et al. A sentiment-aware deep learning approach for personality detection from text[J]. Information processing and management, 2021, 58(3): 102532.
[22] Wikipedia. Social bot[EB/OL]. [2025-04-04]. https://en.wikipedia.org/wiki/Social_bot.
[23] 师文, 陈昌凤. 分布与互动模式: 社交媒体机器人操纵Twitter上的中国议题研究[J]. 国际新闻界, 2020, 42(5): 61-80. (SHI W, CHEN C F. Distribution and interaction patterns: how social bots manipulate the chinese-related issues on Twitter[J]. Chinese journal of journalism & communication, 2020, 42(5): 61-80.)
[24] -GALINDO JP, MARMOL FG, PEREZ GM. Profiling users and bots in Twitter through social media analysis[J]. Information sciences, 2022, 613: 161-183.
[25] HAJLI N, SAEED U, TAJVIDI M, et al. Social bots and the spread of disinformation in social media: the challenges of artificial intelligence[J]. British journal of management, 2022, 33(3): 1238-1253.
[26] 张梦晗, 陈泽. 信息迷雾视域下社交机器人对战时宣传的控制及影响[J]. 新闻与传播研究, 2023, 30(6): 86-105, 128. (ZHANG M H, CHEN Z. The control and influence of war propaganda in social bots conflicts: a perspective from the disinformation fog[J]. Journalism & communication, 2023, 30(6): 86-105, 128.)
[27] ORABI M, MOUHEB D, AL A Z, et al. Detection of bots in social media: a systematic review[J]. Information processing & management, 2020, 57(4): 102250.
[28] 李佳轩, 储节旺, 杜秀秀. 关联、黑箱与赋能: AIGC驱动智慧图书馆的转型路径[J]. 图书情报工作, 2023, 67(23): 18-27. (LI J X, CHU J W, DU X X. Connection, black box and empowerment: the path of AIGC to drive the transformation of smart libraries[J]. Library and information service, 2023, 67(23): 18-27.)
[29] CHOI M, ROMERO DM, JURGENS D. Profile update: the effects of identity disclosure on network connections and language[J]. EPJ data science, 2024, 13(1): 45.
[30] 迈尔斯. 管理与组织研究必读的40个理论[M]. 徐世勇, 李超平, 等译. 北京: 北京大学出版社, 2017. (JEFFREY A M. 40 must - read theories for management and organization studies[M]. XU S Y, LI C P, trans. Beijing: Peking University Press, 2017.)
[31] 唐江浩, 李睿, 王亚楠. 微博“图书馆”热点话题的主题特征分析及启示[J]. 图书情报工作, 2024, 68(18): 87-96. (TANG J H, LI R, WANG Y N. Analysis and inspiration on the thematic characteristics of the hot topics of “Library” on Weibo[J]. Library and information service, 2024, 68(18): 87-96.)
[32] WANG D D, ZHOU Y D, MA F C. Opinion leaders and structural hole spanners influencing echo chambers in discussions about COVID-19 vaccines on social media in China: network analysis[J]. Journal of medical internet research, 2022, 24(11): e40701.
[33] WU Y H, FANG Y Z, SHANG S K, et al. A novel framework for detecting social bots with deep neural networks and active learning[J]. Knowledge-based systems, 2021.
[34] 周潇, 高雅倩, 樊嘉逸. 基于BERT词嵌入的专利检索策略研究[J]. 情报学报, 2023, 42(11): 1347-1357. (ZHOU X, GAO Y Q, FAN J Y. Research on patent retrieval strategy based on BERT word embedding[J]. Journal of the China Society for Scientific and Technical Information, 2023, 42(11): 1347-1357.)
[35] GROOTENDORST M. BERTopic: neural topic modeling with a class-based TF-IDF procedure[J]. arXiv preprint arXiv:2203.05794, 2022.
[36] NEU D, SAXTON G D. Twitter bots, democratic deliberation and social accountability: the case of #OccupyWallStreet[J]. Accounting, auditing & accountability journal, 2025, 38(3): 934-964.
[37] UNLU A, TRUONG S, SAWHNEY N, et al. Tracing the dynamics of misinformation and vaccine stance in Finland amid COVID-19[J]. Information, communication & society, 2025, 28(2): 193-217.
[38] SHAHBAZI M, BUNKER D. Social media trust: fighting misinformation in the time of crisis[J]. Information journal of information management, 2024, 77: 102780.
[39] WANG D D, ZHOU Y D, QIAN Y X, et al. The echo chamber effect of rumor rebuttal behavior of users in the early stage of COVID-19 epidemic in China[J]. Computers in human behavior, 2022, 128: 107088.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References