Social networks, computational intelligence and electoral prediction: the case of the presidential primaries of Chile 2017

Authors

  • Pedro Santander Pontificia Universidad Católica de Valparaíso (Chile)
  • Claudio Elórtegui Pontificia Universidad Católica de Valparaíso (Chile)
  • Cristian González Pontificia Universidad Católica de Valparaíso (Chile)
  • Héctor Allende-Cid Pontificia Universidad Católica de Valparaíso (Chile)
  • Wenceslao Palma Pontificia Universidad Católica de Valparaíso Chile

DOI:

https://doi.org/10.7764/cdi.41.1218

Keywords:

electoral prediction, social networks, primary elections, political communication, Twitter, computational intelligence

Abstract

This article shows the results of an interdisciplinary research applied to the predictive capacity of social networks, specifically Twitter, in the legal primaries in Chile in 2017. Through the incorporation of computational intelligence, we monitored the interaction of all Chilean users who mentioned at least once some of the five candidates competing to design a forecast model that considered the context of political communication, which delivered results under 2% in the mean absolute error (MAE), with more precision than the electoral polls

Author Biographies

Pedro Santander, Pontificia Universidad Católica de Valparaíso (Chile)

Bachelor of Communication and Ph.D. in Linguistics. Professor at the Journalism School of the Pontificia Universidad Católica de Valparaíso, researcher in the area of discourse analysis and media analysis.

Claudio Elórtegui, Pontificia Universidad Católica de Valparaíso (Chile)

Ph.D. in Journalism and Communication Sciences from the Autonomous University of Barcelona. Professor of the School of Journalism of the Pontificia Universidad Católica de Valparaíso, researcher in the area of political communication.

Cristian González, Pontificia Universidad Católica de Valparaíso (Chile)

Ph.D. in Linguistics from the Pontificia Universidad Católica de Valparaíso, Chile, and Ph.D. in Language Sciences from the Paris 13 University, France. He is currently an associate professor at the Institute of Literature and Language Sciences of the Pontificia Universidad Católica de Valparaíso, where he teaches undergraduate and postgraduate programs. He conducts researchs in the field of discourse linguistics, from a semi-linguistic perspective, centered on journalistic, political and academic discourse.

Héctor Allende-Cid, Pontificia Universidad Católica de Valparaíso (Chile)

Ph.D. in Computer Engineering from the Federico Santa María Technical University. He is a professor and researcher at the School of Computer Engineering of the Pontificia Universidad Católica de Valparaíso in the area of automated learning and pattern recognition.

Wenceslao Palma, Pontificia Universidad Católica de Valparaíso Chile

Ph.D. in Computer Science from the University of Nantes. He is a professor and researcher at the School of Computer Engineering of the Pontificia Universidad Católica de Valparaíso in the Big Data area.

References

Aguado, J. & Navarro, H. (2013). Comunicación móvil, ecosistema digital e industrias culturales. In J. Aguado, C. Feijóo, & I. Martínez (coords.). La comunicación móvil. Hacia un nuevo ecosistema digital [Mobile communication: Towards a new digital ecosystem]. Barcelona: Gedisa.
Aparaschivei, P. (2011). The Use of Media in Electoral Campaigns: Analysis on the Use of Blogs, Facebook, Twitter and YouTube in the 2009 Romanian Presidential Campaign. Journal of Media Research, 4(2), 39–60. Retrieved from http://www.mrjournal.ro/docs/R2/10MR5.pdf
Bakliwal, A., Foster, J., van der Puil, J., O’Brien, R., Tounsi, L., & Hughes, M. (2013). Sentiment Analysis of Political Tuits: Towards an Accurate Classifier. In Proceedings of the Workshop on Language Analysis in Social Media (pp. 49–58). Stroudsburg, PA: Association for Computational Linguistics.
Bermingham, A. & Smeaton, A. F. (2011). On using Twitter to monitor political sentiment and predict election results. In Proceedings of the Workshop on Sentiment Analysis where AI meets Psychology (SAAIP) (pp. 2-10). Chiang Mai, Thailand: Workshop at the International Joint Conference for Natural Language Processing. Retrieved from http://doras.dcu.ie/16670/
Boczkowski, P. (2016). Los diarios con Hillary, los fans con Trump. Campañas, medios y mensajes [The newspapers with Hillary, the fans with Trump. Campaigns, media and messages]. Revista Anfibia. Retrieved from http://www.revistaanfibia.com/ensayo/los-diarios-hillary-los-fans-trump/
Campos, F. (2008). Las redes sociales trastocan los modelos de los medios de comunicación tradicionales [Social networks disrupt traditional media models]. Revista Latina de Comunicación Social, 11(63), 287-293. https://doi.org/10.4185/RLCS-63-2008-767-287-293
Castells, M. (2009). Comunicación y Poder [Communication power]. Madrid: Alianza Editorial.
Castells, M. (2015). Redes de indignación y esperanza [Indignation and hope networks]. Madrid: Alianza Editorial.
Ceron, A., Curini, L., & Iacus, S. (2017). Politics and Big Data. London: Routledge
Congosto M., Fernández, M., & Moro, E. (2011). Twitter y política: información, opinión y ¿predicción? [Twitter and politics: information, opinion and prediction?]. Cuadernos de comunicación Evoca, (4), 11-16. Retrieved from http://neolabs.es/evoca/down/cuadernos4.pdf
Cotarelo, R. (Coord.) (2013). Ciberpolítica. Las nuevas formas de acción y la comunicación política [Cyberpolitics. New forms of action and political communication]. Valencia: Tirant Lo Blanc.
Deltell, L., Claes, F., & Osteso, J. (2013). Predicción de tendencia política por Twitter: Elecciones Andaluzas 2012 [Political Trends Prediction on Twitter: Andalusian Election, 2012]. Ámbitos. Revista Internacional de Comunicación, (22), 91-100. Retrieved from http://institucional.us.es/ambitos/?P=148
Fábrega, J. & Paredes, P. (2012). La política chilena en 140 caracteres [Chilean Politics in 140 Characters]. In A. Arriagada & P. Navia (Eds.), Intermedios. Medios de comunicación y democracia en Chile [Intermedia. Media and democracy in Chile] (pp. 199-224). Santiago: Universidad Diego Portales.
Feijóo, C., Maghiros, I., Abadie, F., & Gómez Barroso, J.L. (2009). Exploring a heterogeneous and fragmented digital ecosystem: Mobile content. Telematics and Informatics, 25(3), 282-292. https://doi.org/10.1016/j.tele.2008.11.009
García, F. (2015). Twitter en las campañas políticas en Latinoamérica [Twitter in Political Campaigns in Latin America]. In D. Ivoskus (Ed.), VI Cumbre Mundial de Comunicación Política [VI World Political Communication Summit]. Santo Domingo: Editorial Funglode.
Gerstlé, J. (2004). La comunication politique [Political communication]. Paris: Éditions Dalloz.
Gutiérrez-Rubí, A. (2011). La política vigilada. La comunicación en la era de Wikileaks [Monitored politics. Communication in the Wikileaks era]. Barcelona: Editorial UOC.
Guzmán, G. & Sánchez Medero, R. (2016). El ecosistema digital de la comunicación política. In R. Sánchez Medero (Ed.), Comunicación Política. Nuevas dinámicas y ciudadanía permanente [Political Communication. New dynamics and permanent citizenship]. Madrid: Tecnos.
Habermas, J. (1986). L’espace public. Archéologie de la publicité comme dimension constitutive de la société bourgeoise [The Structural Transformation of the Public Sphere: An Inquiry into a Category of Bourgeois Society]. Paris: Payot.
Harvey, L. (2013). Communication Issues and policy implications. In F. Biocca & M. Levy (Eds.). Communication in the age of virtual reality. New Jersey: Lawrence Erlbaum Associates.
Hilbert, M. (2017). The More You Know, the More You Can Grow: An Information Theoretic Approach to Growth in the Information Age. Entropy, 19(2), 82. https://doi.org/10.3390/e19020082
Issenberg, S. (2012). The Victory Lab. New York: Crown Publishers.
Jenkins, H. (2006). Convergence culture. Where old and new media collide. New York: University Press.
Larsson, A. O. & Moe, H. (2011). Studying political microblogging: Twitter users in the 2010 Swedish election campaign. New Media and Society, 14(5), 729-747. https://doi.org/10.1177/1461444811422894
Lippmann, W. (1922). Public opinion. New York: Harcourt, Brace and Co.
Magnani, E. (2017). Big data y política. El poder de los algoritmos [Big data and politics. The Power of Algorithms]. Nueva Sociedad, (269), 45-55. Retrieved from http://nuso.org/articulo/big-data-y-politica/
McCombs, M. & Shaw, D. (1972). The agenda setting function of mass media. The Public Opinion Quarterly, 36(2), 176-187. https://doi.org/10.1086/267990
McQuail, D. (1991). Introducción a la teoría de la comunicación de masas [Introduction to the mass communication theory]. Barcelona: Paidós.
Momoc, A. (2013). Social Media - PR Tools for Romanian Politicians? Procedia-Social and Behavioral Sciences, 81, 116-121. https://doi.org/10.1016/j.sbspro.2013.06.398
Noëlle-Neumann, E. (1995). La espiral del silencio. Opinión pública: nuestra piel social [The spiral of silence. Public opinion: our social skin]. Barcelona: Paidós.
Ochigame, R. & Holston, J. (2016) Filtering Dissent. Social Media and Land Struggles in Brazil. New Left Review, (99), 85-108. Retrieved from https://newleftreview.org/II/99/rodrigo-ochigame-Jamesholston-filtering-dissent
Pang, B., Lee, L., & Vaithyanathan, S. (2002). Thumbs up?: sentiment classification using machine learning techniques. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10 (pp. 79-86). Stroudsburg, PA: Association for Computational Linguistics.
Price, V. (1994). La Opinión Pública [Public opinion]. Madrid: Gedisa.
Provost, F. & Fawcett, T. (2013). Data Science and its Relationship to Big Data and Data-Driven Decision Making. Big Data, 1(1), 51-59. https://doi.org/10.1089/big.2013.1508
Riquelme, F. & González-Cantergiani P. (2016). Measuring user influence on Twitter. Information Processing & Management, 52(5), 949–975. https://doi.org/10.1016/j.ipm.2016.04.003
Rogers, R. (2004). Information Politics on the Web. Cambridge, MA: MIT Press.
Russell, S. J., Norvig, P., & Davis, E. (2016). Artificial intelligence: a modern approach. Harlow: Prentice Hall.
Sánchez Medero, R. (2016). Nuevos métodos para viejos propósitos: marketing político para el siglo XXI [New Methods for Old Purposes: Political Marketing for the 21st Century]. Cuadernos Hispanoamericanos, (792), 25-41. Retrieved from https://issuu.com/publicacionesaecid/docs/web_cha_792_junio_2016
Schoen, H., Gayo-Avello, D., Takis Metaxas, P., Mustafaraj, E., Strohmaier, M., & Gloor, P. (2013). The power of prediction with social media. Internet Research, 23(5), 528-543. https://doi.org/10.1108/IntR-06-2013-0115
Scolari, C. (2012). Media ecology: exploring the metaphor to expand the theory. Communication Theory, 22(2), 204-225. https://doi.org/10.1111/j.1468-2885.2012.01404.x
Scolari, C. (2013). Narrativas transmedia. Cuando todos los medios cuentan [Transmedia Narrative: when all media count]. Barcelona: Deusto.
Scolari, C. (2015). Ecología de los medios. Entorno, evoluciones e interpretaciones [Media ecology: Environment, evolutions and interpretations]. Barcelona: Gedisa.
Sebastiani, F. (2002). Machine Learning in Automated Text Categorization. ACM Computing Surveys (CSUR), 34(1), 1–47. https://doi.org/10.1145/505282.505283
Taylor, S. & Lethman, B. (2017). Forecasting at scale. The American Statistician (accepted author version posted online). http://doi.org/10.1080/00031305.2017.1380080
Thompson, J. (1998). Los media y la modernidad. Una teoría de los medios de comunicación [The Media and Modernity: A Social Theory of the Media]. Barcelona: Paidós Comunicación.
Tumasjan, A., Sprenger, T., Sandner, P., & Welpe, I. (2010) Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment. Icwsm, 10(1), 178-185. Retrieved from http://www.aaai.org/ocs/index.php/ICWSM/ICWSM10/paper/view/1441.
Van Dijck, J. (2016). La cultura de la conectividad: una historia crítica de las redes sociales [The Culture of Connectivity: A Critical History of Social Media]. Buenos Aires: Siglo Veintiuno Editores.
Varol, O., Ferrara, E., Davis, C., Menczer, F., & Flammini, A. (2017). Online Human-Bot Interactions: Detection, Estimation, and Characterization. arXiv preprint arXiv:1703.03107. Retrieved from https://arxiv.org/pdf/1703.03107.pdf?ref=il
Wescott, N. (2008). Digital Diplomacy: The Impact of the Internet on International Relations. Oxford Internet Institute Research Paper Series, (16), 1-20. https://doi.org/10.2139/ssrn.1326476
Willmott, C. J. & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79–82. https://doi.org/10.3354/cr030079
Zhang, Y., Jin, R., & Zhou, Z.-H. (2010). Understanding bag-of-words model: a statistical framework. International Journal of Machine Learning and Cybernetics, 1(1–4), 43–52. https://doi.org/10.1007/s13042-010-0001-0

Published

2017-12-30

How to Cite

Santander, P. ., Elórtegui, C. ., González, C., Allende-Cid, H. ., & Palma, . W. . (2017). Social networks, computational intelligence and electoral prediction: the case of the presidential primaries of Chile 2017. Cuadernos.Info, (41), 41–56. https://doi.org/10.7764/cdi.41.1218