Abstract：In the context of social media increasingly becoming an important platform for the spread of public opinion, social bots have malicious guidance and manipulation of online public opinion. In order to explore its guidance mechanism, this paper combines the classic Hegselmann-Krause model with the continuous action learning automaton algorithm (CALA), uses a multi-agent method to model the interaction between social bots and individual users, and captures the distribution characteristics of online public opinion through simulation. Experimental results show that social bots can effectively use the CALA algorithm to obtain network attention in different complex environments and guide the opinions of user groups to develop in the direction of predetermined goals. The study verifies the feasibility of bots in public opinion guidance.
[1] SCHMUCK D, SIKORSKI C V. Perceived threats from social bots: the media's role in supporting literacy[J]. Computers in Human Behavior, 2020, 113: 106507. [2] GUENON N M D, SCOTT D H, ZAKARIA H E, et al. Detecting bots and assessing their impact in social networks[J]. Operations Research, 2022, 70(1): 1-22. [3] ZHANG Y, SONG W, SHAO J, et al. Social bots' role in the COVID-19 pandemic discussion on Twitter[J]. International Journal of Environmental Research and Public Health, 2023, 20(4): 3284. [4] ZENG Z, LI T, SUN J, et al. Research on the generalization of social bot detection from two dimensions: feature extraction and detection approaches[J]. Data Technologies and Applications, 2023, 57(2): 177-198. [5] MALIK N, KAR A K, TRIPATHI S N, et al. Exploring the impact of fairness of social bots on user experience[J]. Technological Forecasting and Social Change, 2023, 197: 122913. [6] KHAUND T, KIRDEMIR B, AGARWAL N, et al. Social bots and their coordination during online campaigns: a survey[J]. IEEE Transactions on Computational Social Systems, 2021, 9(2): 530-545. [7] 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. [8] LIU X, ZHAN Y, JIN H, et al. Research on the classification methods of social bots[J]. Electronics, 2023, 12(14): 3030. [9] ZHANG Y, MA J, FANG F. How social bots can influence public opinion more effectively: right connection strategy[J]. Physica A: Statistical Mechanics and Its Applications, 2024, 633: 129386. [10] POZZANA I, FERRARA E. Measuring bot and human behavioral dynamics[J]. Frontiers in Physics, 2020, 8: 125. [11] SHI W, LIU D, YANG J, et al. Social bots' sentiment engagement in health emergencies: a topic-based analysis of the COVID-19 pandemic discussions on Twitter[J]. International Journal of Environmental Research and Public Health, 2020, 17(22): 8701. [12] GRIMME C, PREUSS M, ADAM L, et al. Social bots: human-like by means of human control?[J]. Big Data, 2017, 5(4): 279-293. [13] ROSS B, PILZ L, CABRERA B, et al. Are social bots a real threat? an agent-basedmodel of the spiral of silence to analyse the impact of manipulative actors in social networks[J]. European Journal of Information Systems, 2019, 28(4): 394-412. [14] CHENG C, LUO Y, YU C. Dynamic mechanism of social bots interfering with public opinion in network[J]. Physica A: Statistical Mechanics and Its Applications, 2020, 551: 124163. [15] LI T, ZHU H. Effect of the media on the opinion dynamics in online social networks[J]. Physica A: Statistical Mechanics and Its Applications, 2020, 551: 124117. [16] CHENG C, GU J, LU S, et al. Modified hegselmann-Krause model for enhancing opinion diversity in social networks[J]. IEEE Access, 2024, 12: 140715-140721. [17] CHENG C, LUO Y, YU C, et al. Social bots and mass media manipulated public opinion through dual opinion climate[J]. Chinese Physics B, 2022, 31(1): 018701. [18] WANG L, BERNARDO C, HONG Y, et al. Consensus in concatenated opinion dynamics with stubborn agents[J]. IEEE Transactions on Automatic Control, 2022, 68(7): 4008-4023. [19] LI K, LIANG H, KOU G, et al. Opinion dynamicsmodel based on the cognitive dissonance: an agent-based simulation[J]. Information Fusion, 2020, 56: 1-14. [20] SCHWEIGHOFER S, GARCIA D, SCHWEITZER F. An agent-basedmodel of multi-dimensional opinion dynamics and opinion alignment[J]. Chaos: an Interdisciplinary Journal of Nonlinear Science, 2020, 30(9): 093139. [21] ROZANOVA L, BOGUÁ M. Dynamical properties of the herding votermodel with and without noise[J]. Physical Review E, 2017, 96(1): 012310. [22] BERNARDO C, ALTAFINI C, PROSKURNIKOV A, et al. Bounded confidence opinion dynamics: a survey[J]. Automatica, 2024, 159: 111302. [23] HEGSELMANN R, KRAUSE U. Opinion dynamics and bounded confidencemodels, analysis, and simulation[J]. Journal of Artificial Societies and Social Simulation, 2002, 5(3): 2. [24] WEISBUCH G, DEFFUANT G, AMBLARD F, et al. Meet, discuss, and segregate[J]. Complexity, 2002, 7(3): 55-63. [25] WANG M, LI F, LIANG D. Opinion dynamics and consensus achievement strategy based on reinforcement learning[C]//2020 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT). Louisville, KY, USA: IEEE, 2020: 1-6. [26] WANG M, LIANG D, XU Z. Consensus achievement strategy of opinion dynamics based on deep reinforcement learning with time constraint[J]. Journal of the Operational Research Society, 2022, 73(12): 2741-2755. [27] GUO S, XU H, XIE G, et al. Reinforcement learning-based consensus reaching in large-scale social networks[C]//International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2023: 169-183. [28] HE Q, LV Y, WANG X, et al. Reinforcement-learning-based dynamic opinion maximization framework in signed social networks[J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 15(1): 54-64. [29] MOERLAND T M, BROEKENS J, PLAAT A, et al. Model-based reinforcement learning: a survey[J]. Foundations and Trends in Machine Learning, 2023, 16(1): 1-118. [30] NIE M, CHEN D, WANG D. Reinforcement learning on graphs: a survey[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023 7(4): 1065-1082. [31] ZHANG C, FANG D, SEN S, et al. Opinion dynamics in gossiper-media networks based on multiagent reinforcement learning[J]. IEEE Transactions on Network Science and Engineering, 2022, 10(2): 1143-1156.
