Predicting public opinion dynamics with the scardo-model

Cover Page

Cite item

Full Text

Abstract

Over the past 20 years, the theory of agent-based social influence models has been actively developing, a trend which is associated with the need to explain opinion formation processes in the context of the digitalization of communication channels and the intensification of information exchange processes. However, the practical side of this theory remains poorly studied. The key reason for this is the difficulties in calibrating model parameters and thus constructing an empirical foundation. This paper validates the SCARDO-model of opinion formation using empirical longitudinal data from the social network VKontakte. The data include three opinion snapshots of a large-scale sample of VKontakte users and a snapshot of their friendship connections. The model parameters are calibrated on the first two snapshots, whereas the third one is used to check the accuracy of the model’s forecast regarding the populations of opinion fractions at the next time moment. The constant trend model serves as a benchmark. The analysis performed shows that, depending on the method of parameter calibration, the prediction of the SCARDO-model can be more or less accurate than those of the constant trend model. At the same time, changes in public opinion in the dataset at hand (despite being sufficient to calibrate the model parameters) are small from the macro-scale point of view and, as a result, the typical value of the forecast error does not exceed one percent of <>.

About the authors

Ivan Vladimirovich Kozitsin

V.A. Trapeznikov Institute of Control Sciences of RAS

Email: kozitsin.ivan@mail.ru
Moscow

References

  1. BAIL C.A., ARGYLE L.P., BROWN T.W., BUMPUS J.P. etal. Exposure to opposing views on social media can increasepolitical polarization // Proc. of the National Academy ofSciences. – 2018. – Vol. 115. No. 37. – P. 9216–9221.
  2. CHATTOE-BROWN E. Why questions like ‘do networksmatter?’ matter to methodology: How Agent-Based Modellingmakes it possible to answer them // Int. Journal of SocialResearch Methodology. – 2021. – Vol. 24. No. 4. – P. 429–442.
  3. COMBS A., TIERNEY G., GUAY B., MERHOUT F. et al.Reducing political polarization in the United States with amobile chat platform // Nature human behaviour. – 2023. –Vol. 7. No. 9. – P. 1454–1461.
  4. DEGROOT M.H. Reaching a consensus // Journal of theAmerican Statistical association. – 1974. – Vol. 69. No. 345. –P. 118–121.
  5. FLACHE A., MAS M., FELICIANI T., CHATTOE-BROWN E.et al. Models of social influence: Towards the next frontiers //Journal of Artificial Societies and Social Simulation. – 2017. –Vol. 20. No. 4.
  6. GEZHA V.N., KOZITSIN I.V. The Effects of Individuals’Opinion and Non-Opinion Characteristics on the Organizationof Influence Networks in the Online Domain // Computers. –2023. – Vol. 12. No. 6. – P. 116.
  7. KEIJZER M., MAS M., FLACHE A. Polarization on socialmedia: Micro-level evidence and macro-level implications //Journal of Artificial Societies and Social Simulation. – 2024. –Vol. 27. No. 1. – P. 1–7.
  8. KOZITSIN I.V. A general framework to link theory andempirics in opinion formation models // Scientific reports. –2022. – Vol. 12. No. 1. – P. 5543.
  9. 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.
  10. MASTROENI L., VELLUCCI P., NALDI M. WAgent-basedmodels for opinion formation: A bibliographic survey // IEEEAccess. – 2019. – Vol. 7. – P. 58836–58848.
  11. MAS M., BISCHOFBERGER L. Will the personalization ofonline social networks foster opinion polarization? // Availableat SSRN 2553436. – 2015.
  12. 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.
  13. ROBERTSON R.E., GREEN J., RUCK D.J., OGNYANOVA K.et al. Users choose to engage with more partisan news than theyare exposed to on Google Search // Nature. – 2023. – P. 1–7.

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).