Abstract
The prediction of opinion distribution in real-world scenarios represents a major scientific challenge for current social networks analysis. In terms of electoral forecasting, we find several prediction solutions that try to combine statistics with economic indices, and machine learning, like multilevel regression and post-stratification (MRP). Nevertheless, recent studies pinpoint toward the importance of temporal characteristics in the diffusion of opinion. As such, we take inspiration from micro-scale temporal epidemic models and develop an original time-aware (TA) forecasting methodology which is able to improve the prediction of opinion distribution in an electoral context. After a parametric analysis, we validate our TA method with pre-election survey data from three presidential elections (2012–2019) and the UK Brexit (2016). Benchmarking our TA method against two classic statistical approaches, like survey averaging (SA), and cumulative vote counting (CC), and the best pollster predictions, we find that our method is substantially closer to the real election outcomes. On average, we measure prediction errors of 9.8% (SA), 9.6% (CC), 5.1% (MRP), and only 3.0% for TA; these differences translate into increases of prediction accuracy of \(\approx 71\%\) for the TA method (40% better than best pollsters). Moreover, TA does not require socio-economical contextual information, while the more complex MRP method depends on them for prediction. This work builds upon existing studies on the microscopic temporal dynamics of social networks and offers new insight on how macroscopic prediction can be improved using time-awareness.
Similar content being viewed by others
Notes
Available online at https://www.realclearpolitics.com.
Available online at https://whatukthinks.org/eu/.
Dataset available online at https://www.realclearpolitics.com/epolls/2012/president/us/general_election_romney_vs_obama-1171.html#polls.
Dataset available online at https://www.realclearpolitics.com/epolls/2016/president/us/general_election_trump_vs_clinton-5491.html#polls.
Dataset available online at https://en.wikipedia.org/wiki/2019_Romanian_presidential_election.
References
Adamic L, Adar E (2005) How to search a social network. Soc Netw 27(3):187–203
Asur S, Huberman BA (2010) Predicting the future with social media. In: Proceedings of the 2010 IEEE/WIC/ACM international conference on web intelligence and intelligent agent technology, vol 01. IEEE Computer Society, pp 492–499
Axelrod R (1997) The dissemination of culture: a model with local convergence and global polarization. J Confl Resolut 41(2):203–226
Barabási A-L (2009) Scale-free networks: a decade and beyond. Science 325(5939):412–413
Barabási A-L, Pósfai M (2016) Network science. Cambridge University Press, Cambridge
Bernhardt D, Krasa S, Polborn M (2008) Political polarization and the electoral effects of media bias. J Public Econ 92(5–6):1092–1104
Cannarella J, Spechler JA (2014) Epidemiological modeling of online social network dynamics. arXiv preprint arXiv:1401.4208
Christensen WF, Florence LW (2008) Predicting presidential and other multistage election outcomes using state-level pre-election polls. Am Stat 62(1):1–10
Conway BA, Kenski K, Wang D (2013) Twitter use by presidential primary candidates during the 2012 campaign. Am Behav Sci 57(11):1596–1610
Coppedge M, Gerring J, Knutsen CH, Lindberg SI, Teorell J, Altman D, Bernhard M, Fish MS, Glynn A, Hicken A, et al (2019) V-dem codebook v9. University of Gothenburg, V-Dem Institute. https://bit.ly/3gUqiR4
Duma A, Topirceanu A (2014) A network motif based approach for classifying online social networks. In: Applied computational intelligence and informatics (SACI). IEEE, pp 311–315
Easley D, Kleinberg J (2010) Networks, crowds, and markets: reasoning about a highly connected world. Cambridge University Press, Cambridge
Feldman A, Konold C, Coulter B, Conroy B (2000) Network science, a decade later: the Internet and classroom learning. Routledge, London
Gladwin H, Lazo JK, Morrow BH, Peacock WG, Willoughby HE (2007) Social science research needs for the hurricane forecast and warning system. Nat Hazards Rev 8(3):87–95
Golbeck J (2013) Analyzing the social web. Access Online via Elsevier
Golbeck J, Hansen D (2014) A method for computing political preference among Twitter followers. Soc Netw 36:177–184
Goldenberg J, Libai B, Muller E (2001) Talk of the network: a complex systems look at the underlying process of word-of-mouth. Mark Lett 12(3):211–223
Gomez-Rodriguez M, Leskovec J, Krause A (2012) Inferring networks of diffusion and influence. ACM TKDD 5(4):21
Graber DA, Dunaway J (2017) Mass media and American politics. CQ Press, Washington
Granovetter M (1978) Threshold models of collective behavior. Am J Sociol 83(6):1420–1443
Grimaldi D (2019) Can we analyse political discourse using twitter? Evidence from Spanish 2019 presidential election. Soc Netw Anal Min 9(1):49
Groves RM (2006) Nonresponse rates and nonresponse bias in household surveys. Public Opin Q 70(5):646–675
Guille A, Hacid H (2012) A predictive model for the temporal dynamics of information diffusion in online social networks. In: Proceedings of the 21st international conference on World Wide Web. ACM, pp 1145–1152
Guille A, Hacid H, Favre C (2012) Predicting the temporal dynamics of information diffusion in social networks. arXiv preprint arXiv:1302.5235
Guille A, Hacid H, Favre C, Zighed DA (2013) Information diffusion in online social networks: a survey. ACM Sigmod Record 42(2):17–28
Heredia B, Prusa JD, Khoshgoftaar TM (2018) Social media for polling and predicting United States election outcome. Soc Netw Anal Min 8(1):48
Holley RA, Liggett TM (1975) Ergodic theorems for weakly interacting infinite systems and the voter model. Ann Probab 3:643–663
Howard PN, Duffy A, Freelon D, Hussain MM, Mari W, Maziad M (2011) Opening closed regimes: what was the role of social media during the Arab spring? SSRN 2595096
Hufnagel L, Brockmann D, Geisel T (2004) Forecast and control of epidemics in a globalized world. Proc Natl Acad Sci 101(42):15124–15129
Hughes AL, Palen L (2009) Twitter adoption and use in mass convergence and emergency events. Int J Emerg Manag 6(3–4):248–260
Hummel P, Rothschild D (2014) Fundamental models for forecasting elections at the state level. Electoral Stud 35:123–139
Hussain MM, Howard PN (2013) What best explains successful protest cascades? ICTs and the fuzzy causes of the Arab spring. Int Stud Rev 15(1):48–66
Jackson MO, Watts A (2002) The evolution of social and economic networks. J Econ Theory 106(2):265–295
Jackson MO, Rogers BW, Zenou Y (2017) The economic consequences of social-network structure. J Econ Lit 55(1):49–95
Karrer B, Newman ME (2011) Competing epidemics on complex networks. Phys Rev E 84(3):036106
Kiewiet de Jonge CP, Langer G, Sinozich S (2018) Predicting state presidential election results using national tracking polls and multilevel regression with poststratification (MRP). Public Opin Q 82(3):419–446
Leskovec J, Adamic LA, Huberman BA (2007) The dynamics of viral marketing. ACM TWEB 1(1):5
Lewis-Beck MS, Skalaban A (1989) Citizen forecasting: can voters see into the future? Br J Polit Sci 19(1):146–153
Lewis-Beck MS, Tien C (1999) Voters as forecasters: a micromodel of election prediction. Int J Forecast 15(2):175–184
Marozzo F, Bessi A (2018) Analyzing polarization of social media users and news sites during political campaigns. Soc Netw Anal Min 8(1):1
McAuley JJ, Leskovec J (2012) Learning to discover social circles in ego networks. NIPS 2012:548–56
Mellon J, Prosser C (2017) Twitter and facebook are not representative of the general population: political attitudes and demographics of British social media users. Res Polit 4(3):2053168017720008
Myers S, Leskovec J (2010) On the convexity of latent social network inference. In: Advances in neural information processing systems, pp 1741–1749
Nadeau R, Lewis-Beck MS, Bélanger É (2010) Electoral forecasting in france: a multi-equation solution. Int J Forecast 26(1):11–18
Nguyen HT, Dinh TN, Thai MT (2016) Cost-aware targeted viral marketing in billion-scale networks. In: IEEE INFOCOM 2016—the 35th annual IEEE international conference on computer communications. IEEE, pp 1–9
Nowzari C, Preciado VM, Pappas GJ (2016) Analysis and control of epidemics: a survey of spreading processes on complex networks. IEEE Control Syst 36(1):26–46
Papasolomou I, Melanthiou Y (2012) Social media: marketing public relations’ new best friend. J Promot Manag 18(3):319–328
Pastor-Satorras R, Castellano C, Van Mieghem P, Vespignani A (2015) Epidemic processes in complex networks. Rev Mod Phys 87(3):925
Rodriguez MG, Balduzzi D, Schölkopf B (2011) Uncovering the temporal dynamics of diffusion networks. arXiv preprint arXiv:1105.0697
Stieglitz S, Dang-Xuan L (2013) Social media and political communication: a social media analytics framework. Soc Netw Anal Min 3(4):1277–1291
Sznajd-Weron K, Sznajd J (2000) Opinion evolution in closed community. Int J Mod Phys C 11(06):1157–1165
Topîrceanu A (2017a) Gamified learning: a role-playing approach to increase student in-class motivation. Procedia Comput Sci 112:41–50
Topîrceanu A (2017b) Breaking up friendships in exams: a case study for minimizing student cheating in higher education using social network analysis. Comput Educ 115:171–187
Topîrceanu A (2018) Competition-based benchmarking of influence ranking methods in social networks. Complexity. https://doi.org/10.1155/2018/4562609. Article ID 4562609
Topîrceanu A, Precup R-E (2019) A novel methodology for improving election poll prediction using time-aware polling. In: Proceedings of the 2019 IEEE/ACM international conference on advances in social networks analysis and mining, pp 282–285
Topirceanu A, Barina G, Udrescu M (2014a) Musenet: collaboration in the music artists industry. In: Network intelligence conference (ENIC), 2014 European. IEEE, pp 89–94
Topirceanu A, Udrescu M, Vladutiu M (2014b) Genetically optimized realistic social network topology inspired by facebook. In: Online social media analysis and visualization. Springer, pp 163–179
Topirceanu A, Udrescu M, Vladutiu M, Marculescu R (2016) Tolerance-based interaction: a new model targeting opinion formation and diffusion in social networks. PeerJ Comput Sci 2:e42
Wallinga J, Teunis P (2004) Different epidemic curves for severe acute respiratory syndrome reveal similar impacts of control measures. Am J Epidemiol 160(6):509–516
Wang W, Rothschild D, Goel S, Gelman A (2015) Forecasting elections with non-representative polls. Int J Forecast 31(3):980–991
Weimann G (1990) The obsession to forecast: pre-election polls in the Israeli press. Public Opin Q 54(3):396–408
Whiteley P (1979) Electoral forecasting from poll data: the British case. Br J Polit Sci 9(2):219–236
Acknowledgements
Author A.T. is supported by the Romanian National Authority for Scientific Research and Innovation (UEFISCDI), Project Number PN-III-P1-1.1-PD-2019-0379.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Topîrceanu, A., Precup, RE. A framework for improving electoral forecasting based on time-aware polling. Soc. Netw. Anal. Min. 10, 39 (2020). https://doi.org/10.1007/s13278-020-00646-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13278-020-00646-7