Abstract
We model the propagation competition between hostile groups as an opinion dynamic game. The model is based on a variant of the DeGroot model. In the cost function, we considered the regulation from the platform and the intention to nudge the opponent against the regulation. Considering the unavailability of network relations, we use reinforcement learning to search for the feedback strategy of both parties. In the simulation, we verified the effectiveness of this method and showed that the stricter the platform regulation, the more conducive to the formation of consensus.
Zusammenfassung
Wir modellieren den Wettbewerb in der Verbreitung zwischen feindlichen Gruppen als ein Meinungsdynamik-Spiel. Das Modell basiert auf einer Variante des DeGroot-Modells. In der Kostenfunktion berücksichtigen wir die Regulierung durch die Plattform und die Absicht, den Gegner gegen die Regulierung zu beeinflussen. Das Problem wird als Differenzspiel formuliert. Angesichts der Nichtverfügbarkeit von Netzwerkbeziehungen verwenden wir verstärkendes Lernen, um die Rückkopplungsstrategie beider Parteien zu lösen. In der Simulation haben wir die Wirksamkeit dieser Methode überprüft und gezeigt, dass strengere Plattformregulierungen eher zur Bildung von Konsens beitragen.
Funding source: National Science Foundation of China
Award Identifier / Grant number: 62373123
About the authors
Yuhong Chen received a B.Eng. degree and a M.Sc. degree in control theory and engineering from the Harbin Institute of Technology, Harbin, China, in 2017 and 2019 respectively. She is currently working toward the Ph.D. degree with the Chair of Automatic Control Engineering, Technical University of Munich, Munich, Germany. Her current research interests include modeling, analysis, and control on social networks.
Cong Li received the Ph.D. degree in learning-based control and robotics with the Chair of Automatic Control Engineering, Technical University of Munich, Munich, Germany. He was also a Research Associate with the Chair of Automatic Control Engineering, Technical University of Munich. His research interests include reinforcement learning, optimal control, robust control, constraint optimization, and robotics.
Fangzhou Liu received the M.Sc. degree in control theory and engineering from the Harbin Institute of Technology, Harbin, China, in 2014 and the Doktor-Ingenieur degree in electrical engineering from the Technical University of Munich, Munich, Germany, in 2019. He was a Lecturer and a Research Fellow with the Chair of Automatic Control Engineering, Technical University of Munich. He is currently a Full Professor with the School of Astronautics, Harbin Institute of Technology. His current research interests include networked control systems, modeling, analysis, and control on social networks, reinforcement learning and their applications. Dr. Liu has received the Dimitris N. Chorafas Prize and the Promotionspreis der Fakultät für Elektrotechnik und Informationstechnik.
Martin Buss received the Diploma Engineering degree in electrical engineering from the Technische Universität Darmstadt, Darmstadt, Germany, in 1990, and the Doctor of Engineering degree in electrical engineering from The University of Tokyo, Tokyo, Japan, in 1994. His research interests include automatic control, mechatronics, multimodal human system interfaces, optimization, nonlinear, and hybrid discrete-continuous systems. He has been awarded the ERC Advanced Grant SHRINE.
Acknowledgement
The authors would like to thank Yilin Wang for helping conduct numerical validations.
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: This work was supported by the National Science Foundation of China (62373123).
-
Data availability: Not applicable.
References
[1] G. Neubaum and N. C. Krämer, “Monitoring the opinion of the crowd: psychological mechanisms underlying public opinion perceptions on social media,” Media Psychol., vol. 20, no. 3, pp. 502–531, 2017. https://doi.org/10.1080/15213269.2016.1211539.Search in Google Scholar
[2] S. Bradshaw and P. Howard, Troops, Trolls and Troublemakers: A Global Inventory of Organized Social Media Manipulation, Oxford, Computational Propaganda Research Project, 2017.Search in Google Scholar
[3] M. Mazza, M. Avvenuti, S. Cresci, and M. Tesconi, “Investigating the difference between trolls, social bots, and humans on Twitter,” Comput. Commun., vol. 196, no. 10, pp. 23–36, 2022. https://doi.org/10.1016/j.comcom.2022.09.022.Search in Google Scholar
[4] Y. Liu, S.-M. Diao, Y.-X. Zhu, and Q. Liu, “SHIR competitive information diffusion model for online social media,” Phys. A, vol. 461, pp. 543–553, 2016. https://doi.org/10.1016/j.physa.2016.06.080.Search in Google Scholar
[5] S. Macedo, “Lost in the marketplace of ideas: towards a new constitution for free speech after Trump and Twitter?,” Philos. Soc. Crit., vol. 48, no. 5, pp. 496–514, 2022. https://doi.org/10.1177/01914537221089363.Search in Google Scholar
[6] B. Fung, Twitter Bans President Trump’s Account, Atlanta, CNN Business, 2021.Search in Google Scholar
[7] M. H. DeGroot, “Reaching a consensus,” J. Am. Stat. Assoc., vol. 69, no. 345, pp. 118–121, 1974. https://doi.org/10.1080/01621459.1974.10480137.Search in Google Scholar
[8] N. E. Friedkin and E. C. Johnsen, “Social influence and opinions,” J. Math. Sociol., vol. 15, nos. 3–4, pp. 193–206, 1990. https://doi.org/10.1080/0022250x.1990.9990069.Search in Google Scholar
[9] N. E. Friedkin and E. C. Johnsen, “Influence networks and opinion change,” Adv. Group Process., vol. 16, no. 1, pp. 1–29, 1999.Search in Google Scholar
[10] H. X. Yang and B. H. Wang, “Effects of social diversity on the evolutionary game and opinion dynamics,” Phys. Procedia, vol. 3, no. 5, pp. 1859–1865, 2010. https://doi.org/10.1016/j.phpro.2010.07.030.Search in Google Scholar
[11] M. Smyrnakis, D. Bauso, and T. Hamidou, “An evolutionary game perspective on quantised consensus in opinion dynamics,” PLoS One, vol. 14, no. 1, p. e0209212, 2019. https://doi.org/10.1371/journal.pone.0209212.Search in Google Scholar PubMed PubMed Central
[12] B. Wu, J. Du, and L. Wang, “Bridging the gap between opinion dynamics and evolutionary game theory: some equivalence results,” in 2020 39th Chinese Control Conference (CCC), IEEE, 2020, pp. 6707–6714.10.23919/CCC50068.2020.9188845Search in Google Scholar
[13] M. U. B. Niazi, A. B. Özgüler, and A. Yildiz, “Consensus as a nash equilibrium of a dynamic game,” in 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), 2016, pp. 365–372.10.1109/SITIS.2016.65Search in Google Scholar
[14] A. A. Sedakov and M. Zhen, “Opinion dynamics game in a social network with two influence nodes,” Vestn. St.-Peterbg. Univ. Prikl. Mat. Inform. Protsessy Upr., vol. 15, pp. 118–125, 2019.10.21638/11701/spbu10.2019.109Search in Google Scholar
[15] M. Zhen, “Stackelberg equilibrium of opinion dynamics game in social network with two influence nodes,” Contrib. Game Theory Manag., vol. 12, no. 1, pp. 366–386, 2019.Search in Google Scholar
[16] V. Mazalov and E. Parilina, “Game of competition for opinion with two centers of influence,” in Mathematical Optimization Theory and Operations Research, Lecture Notes in Computer Science, (Cham), M. Khachay, Y. Kochetov, and P. Pardalos, Eds., Springer International Publishing, 2019, pp. 673–684.10.1007/978-3-030-22629-9_47Search in Google Scholar
[17] V. Mazalov and E. Parilina, “The euler-equation approach in average-oriented opinion dynamics,” Mathematics, vol. 8, no. 3, p. 355, 2020. https://doi.org/10.3390/math8030355.Search in Google Scholar
[18] H. Jiang, V. V. Mazalov, H. Gao, and C. Wang, “Opinion dynamics control in a social network with a communication structure,” Dyn. Games Appl., vol. 13, no. 11, pp. 412–434, 2023.Search in Google Scholar
[19] M. T. Agieva, A. V. Korolev, and G. A. Ougolnitsky, “Game theoretic models of sustainable management in marketing networks,” Contrib. Game Theory Manag., vol. 13, pp. 24–56, 2020. https://doi.org/10.21638/11701/spbu31.2020.03.Search in Google Scholar
[20] M. T. Agieva, A. V. Korolev, and G. A. Ougolnitsky, “Modeling and simulation of impact and control in social networks with application to marketing,” Mathematics, vol. 8, p. 1529, 2020. https://doi.org/10.3390/math8091529.Search in Google Scholar
[21] M. T. Agieva, O. I. Gorbaneva, and G. A. Ougolnitsky, “Dynamic SPICE-model of resource allocation in marketing networks with Co-directed interests,” in 2020 2nd International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA), 2020, pp. 161–165.10.1109/SUMMA50634.2020.9280699Search in Google Scholar
[22] D. A. Broniatowski, et al.., “Weaponized health communication: twitter bots and Russian trolls amplify the vaccine debate,” Am. J. Public Health, vol. 108, no. 9, pp. 1378–1384, 2018. https://doi.org/10.2105/ajph.2018.304567.Search in Google Scholar
[23] I. Garibay, A. V. Mantzaris, A. Rajabi, and C. E. Taylor, “Polarization in social media assists influencers to become more influential: analysis and two inoculation strategies,” Sci. Rep., vol. 9, 2019, no. 1. https://doi.org/10.1038/s41598-019-55178-8.Search in Google Scholar PubMed PubMed Central
[24] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, Cambridge, MIT press, 2018.Search in Google Scholar
[25] A. Al-Tamimi, F. L. Lewis, and M. Abu-Khalaf, “Model-free q-learning designs for linear discrete-time zero-sum games with application to h-infinity control,” Automatica, vol. 43, no. 3, pp. 473–481, 2007. https://doi.org/10.1016/j.automatica.2006.09.019.Search in Google Scholar
[26] K. E. Pearce, “Democratizing kompromat: the affordances of social media for state-sponsored harassment,” Inf. Commun. Soc., vol. 18, no. 10, pp. 1158–1174, 2015. https://doi.org/10.1080/1369118x.2015.1021705.Search in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston
