Forecasting the dynamics of public opinion based on longitudinal data of high granularity: the abelson model, regression models, and ensembles of models

Cover Page

Cite item

Full Text

Abstract

We consdier the problem of forecasting the dynamics of public opinion based on longitudinal data of high granularity gleaned from the social network VKontakte. This problem was suggested to the participants of the Hackathon "UBS Challenge'2024" as one of the leisure events of the XX All-Russian School-Conference of Young Scientists "Management of Large Systems" (UBS), held in Novocherkassk in 2024. This paper is devoted to a detailed description of the Hackathon and the solutions proposed by its participants. For a sample of N = 1 648 829 users, based on two granular snapshots of their opinions taken six months apart (in February and July 2018), participants have to elaborate on a forecast of the distribution of public opinion in December 2018. The participants also had the information about the structure of friendship ties between users. We report that the highest accuracy was achieved by an ensemble of two models -- the Abelson model, enhanced by estimating users' social power via the eigenvector centrality measure, and the constant trend model.

About the authors

Maksim Emonayevich Buzikov

V.A. Trapeznikov Institute of Control Sciences of RAS

Email: me.buzikov@physics.msu.ru
Moscow

Iuliia Aleksandrovna Petelina

Ozon Tech

Email: ptlna@yandex.ru
Moscow

Semen Aleksandrovich Krassotkin

V.A. Trapeznikov Institute of Control Sciences of RAS

Email: semen.krassotkin@gmail.com
Moscow

Maksin Sergeevich Ryzhov

V.A. Trapeznikov Institute of Control Sciences of RAS

Email: ryzhov@phystech.edu
Moscow

Ivan Vladimirovich Kozitsin

V.A. Trapeznikov Institute of Control Sciences of RAS, Moscow, Moscow Institute of Physics and Technology

Email: kozisin.ivan@mail.ru
Moscow

References

  1. ABELSON R.P. Mathematical models of the distribution ofattitudes under controversy // Contributions to MathematicalPsychology. – 1964.
  2. BONACICH P. Some unique properties of eigenvectorcentrality // Social Networks. – 2007. – Vol. 29, No. 4. – P. 555–564. – DOI: https://doi.org/10.1016/j.socnet.2007.04.002.
  3. BOND R.M. et al. A 61-million-person experiment insocial influence and political mobilization // Nature. –2012. – Vol. 489, No. 7415. – P. 295–298. – DOI: https://doi.org/10.1038/nature11421.
  4. CHEBOTAREV P., GUBANOV D.A. How to Choose the MostAppropriate Centrality Measure? A Decision-Tree Approach //IEEE Trans. on Systems, Man, and Cybernetics: Systems. –2024. – DOI: https://doi.org/10.1109/TSMC.2024.3510633.
  5. CINUS F. et al. The effect of people recommenders on echochambers and polarization // Proc. of the Int. AAAI Conf. onWeb and Social Media. – 2022. – Vol. 16. – P. 90–101. – DOI:https://doi.org/10.1609/icwsm.v16i1.19275.
  6. DEFFUANT G. et al. Mixing beliefs among interacting agents //Advances in Complex Systems. – 2000. – Vol. 3, No. 01n04. –P. 87–98. – DOI: https://doi.org/10.1142/S0219525900000078.
  7. DEGROOT M.H. Reaching a consensus // Journal ofthe American Statistical association. – 1974. – Vol.69, No. 345. – P. 118–121. – DOI: https://doi.org/10.1080/01621459.1974.10480137.
  8. FLACHE A. et al. Models of social influence: Towards the nextfrontiers // JASSS – The Journal of Artificial Societies andSocial Simulation. – 2017. – Vol. 20, No. 4. – P. 2. – DOI:https://doi.org/10.18564/jasss.3521.
  9. FRENCH JR J.R.P. A formal theory of social power //Psychological Review. – 1956. – Vol. 63, No. 3. – P. 181.
  10. FREY V. et al. Who influences lower-status individualsmore: People of higher-status outgroups or people of theirlower-status ingroup? Examining the difference betweenmatters of opinion and matters of fact // Social ScienceResearch. – 2024. – Vol. 123. – P. 103060. – DOI: https://doi.org/10.1016/j.ssresearch.2024.103060.
  11. FRIEDKIN N.E., JIA P., BULLO F. A theory of the evolutionof social power: Natural trajectories of interpersonal influencesystems along issue sequences // Sociological Science. – 2016. –Vol. 3. – P. 444–472. – DOI: https://doi.org/10.15195/v3.a20.
  12. GEZHA V.N., KOZITSIN I.V. The effects of individuals’opinion and non-opinion characteristics on theOrganization of Influence Networks in the online domain //Computers. – 2023. – Vol. 12, No. 6. – P. 116. – DOI:https://doi.org/10.3390/computers12060116.
  13. JEDRZEJEWSKI A., SZNAJD-WERON K. Impact of memoryon opinion dynamics // Physica A: Statistical Mechanics andits Applications. – 2018. – Vol. 505. – P. 306–315. – DOI:https://doi.org/10.1016/j.physa.2018.03.077.
  14. JI C., JIANG D. Threshold behaviour of a stochasticSIR model // Applied Mathematical Modelling. – 2014. –Vol. 38, No. 21–22. – P. 5067–5079. – DOI: https://doi.org/10.1016/j.apm.2014.03.037.
  15. KOZITSIN I.V. et al.Modeling political preferencesof russian users exemplified by the social networkVkontakte // Mathematical Models and ComputerSimulations. – 2020. – Vol. 12. – P. 185–194. – DOI: https://doi.org/10.1134/S2070048220020088.
  16. KOZITSIN I.V. A general framework to link theory andempirics in opinion formation models // Scientific reports. –2022. – Vol. 12, No. 1. – P. 5543. – DOI: https://doi.org/10.1038/s41598-022-09468-3.
  17. KOZITSIN I.V. Opinion dynamics of online social networkusers: a micro-level analysis // The Journal of MathematicalSociology. – 2023. – Vol. 47, No. 1. – P. 1–41. – DOI:https://doi.org/10.1080/0022250X.2021.1956917.
  18. KULKARNI B. et al. SLANT+: A nonlinear model foropinion dynamics in social networks // IEEE Int. Conf. onData Mining (ICDM). – IEEE, 2017. – P. 931–936. – DOI:https://doi.org/10.1109/ICDM.2017.117.
  19. NEWMAN M. Networks. – Oxford University Press, 2018.
  20. OKAWA M., IWATA T. Predicting opinion dynamicsvia sociologically-informed neural networks // Proc. ofthe 28th ACM SIGKDD Conf. on Knowledge Discoveryand Data Mining. – 2022. – P. 1306–1316. – DOI:https://doi.org/10.1145/3534678.35392.
  21. PANSANELLA V. et al. Change my mind: Data drivenestimate of open-mindedness from political discussions //Int. Conf. on Complex Networks and Their Applications. –Cham: Springer Int. Publishing, 2022. – P. 86–97. – DOI:https://doi.org/10.1007/978-3-031-21127-0_8.
  22. PESHKOVSKAYA A., BABKINA T., MYAGKOV M. Socialcontext reveals gender differences in cooperative behavior //Journal of Bioeconomics. – 2018. – Vol. 20. – P. 213–225. –DOI: https://doi.org/10.1007/s10818-018-9271-5.
  23. PESHKOVSKAYA A., BABKINA T., MYAGKOV M. Gendereffects and cooperation in collective action: A laboratoryexperiment // Rationality and Society. – 2019. – Vol. 31, No. 3. –P. 337–353. – DOI: https://doi.org/10.1177/1043463119858788.
  24. PROSKURNIKOV A.V., TEMPO R. A tutorial on modelingand analysis of dynamic social networks. Part I // AnnualReviews in Control. – 2017. – Vol. 43. – P. 65–79. – DOI:https://doi.org/10.1016/j.arcontrol.2017.03.002.
  25. PROSKURNIKOV A.V., TEMPO R. A tutorial on modelingand analysis of dynamic social networks. Part II // AnnualReviews in Control. – 2018. – Vol. 45. – P. 166–190. – DOI:https://doi.org/10.1016/j.arcontrol.2018.03.005.
  26. RAVAZZI C. et al. Learning hidden influences in large-scale dynamical social networks: A data-driven sparsity-basedapproach, in memory of Roberto Tempo // IEEE ControlSystems Magazine. – 2021. – Vol. 41, No. 5. – P. 61–103. –DOI: https://doi.org/10.1109/MCS.2021.3092810.
  27. ZHU L., HE Y., ZHOU D. Neural opinion dynamics modelfor the prediction of user-level stance dynamics // InformationProcessing & Management. – 2020. – Vol. 57, No. 2. –P. 102031. – DOI: https://doi.org/10.1016/j.ipm.2019.03.010.
  28. КОЗИЦИН И.В. Построение прогноза динамики обще-ственного мнения при помощи SCARDO-модели // Управ-ление большими системами. – 2024. – Вып. 108. – С. 124–136. – DOI: https://doi.org/10.25728/ubs.2024.108.7.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).