Predictive Model for Brazilian Presidential Election Based on Analysis of Social Media

  • Guilherme Silva
  • Mirele Costa
  • André Drummond
  • Li WeigangEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)


The prediction of presidential election outcome is key point of interest for politicians, electors and sponsoring companies. The 2018 Brazilian election presented a scenario with many uncertainties increasing prediction challenge. The utilization of social media as the promotion tools is another new scenario for both election and also prediction. In this paper, we present a Bayesian forecasting model based on the data from public opinion polls to predict the votes of undecided voters, about a third of the population. The migration of votes among candidates during the electoral period was also analyzed. By using the data from social media in the decision-making process, the proposed model and application show the capability to estimate the voting numbers of the main candidates with better accuracy than public opinion polls.


Forecasting Brazilian election Naive Bayes Social media 


  1. 1.
    Netto, V.: Lava Jato - o juiz Sérgio Moro e os bastidores da operação que abalou o Brasil, 1st edn. Rio de Janeiro, Primeira Pessoa - Selo da Editora Sextante (2016)Google Scholar
  2. 2.
    Igbokwe-Ibeto, C.J., et al.: Election and democratic consolidation in Nigeria: an analysis of the 2015 general elections. Arab. J. Bus. Manag. Rev. 5(10), 1–16 (2016)Google Scholar
  3. 3.
    Suryani, D.: Defending democracy: citizen participation in election monitoring in post-authoritarian Indonesia. J. Stud. Pemerintah. 6(1), 1–17 (2015). ISSN 2337-8220Google Scholar
  4. 4.
    Mendoza, M., Nieto-Barajas, L.E.: Quick counts in the Mexican presidential elections: a Bayesian approach. Elect. Stud. 43, 124–132 (2016)CrossRefGoogle Scholar
  5. 5.
    Hummel, P., Rothschild, D.: Fundamental models for forecasting elections at the state level. Elect. Stud. 35, 123–139 (2014). Scholar
  6. 6.
    Linzer, D.A.: Dynamic Bayesian forecasting of presidential elections in the states. J. Am. Stat. Assoc. 108(501), 124–134 (2013)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Lock, K., Gelman, A.: Bayesian combination of state polls and election forecasts. Polit. Anal. 18(3), 337–348 (2010). Scholar
  8. 8.
    Yang, P., Chen, Y.: A survey on sentiment analysis by using machine learning methods. In: Technology Networking Electronic and Automation Control Conference (ITNEC), pp. 117–121 (2017)Google Scholar
  9. 9.
    Hussein, D.M.E.D.M.: A survey on sentiment analysis challenges. J. King Saud Univ. Eng. Sci. 30(4), 330–338 (2018)Google Scholar
  10. 10.
    Joyce, B., Deng, J.: Sentiment analysis of tweets for the 2016 US presidential election. In: IEEE MIT Undergraduate Research Technology Conference, pp. 1–4 (2017)Google Scholar
  11. 11.
    Yaqub, U., et al.: Analysis of political discourse on twitter in the context of the 2016 US presidential elections. Gov. Inf. Q. 34(4), 613–626 (2017)CrossRefGoogle Scholar
  12. 12.
    Machado, C., et al.: News and political information consumption in Brazil: mapping the first round of the 2018 Brazilian presidential election on Twitter. COMPROP Data Memo (2018)Google Scholar
  13. 13.
  14. 14.
  15. 15.
    Lewis, D.D.: Naive (Bayes) at forty: the independence assumption in information retrieval. In: Nédellec, C., Rouveirol, C. (eds.) Machine Learning: ECML-1998. Springer, Heidelberg (1998)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Guilherme Silva
    • 1
    • 2
  • Mirele Costa
    • 1
  • André Drummond
    • 1
  • Li Weigang
    • 1
    Email author
  1. 1.Department of Computer ScienceUniversity of BrasiliaBrasiliaBrazil
  2. 2.Department of Electrical EngineeringState University of PiauíTeresinaBrazil

Personalised recommendations