Publicado

2023-03-10

Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework

¿Los patrones de búsqueda en Internet predicen los resultados de las elecciones? Un análisis de las elecciones presidenciales de 2022 en Colombia utilizando un marco de análisis descriptivo reproducible

DOI:

https://doi.org/10.15446/dyna.v90n225.104189

Palabras clave:

analítica electoral; tendencias de Google; analítica descriptiva; elecciones presidenciales (es)
electoral analytics; Google Trends; analytics; descriptive analytics; presidential elections (en)

Autores/as

Trabajos recientes resaltan la pertinencia de los datos de Tendencias de Google para predecir procesos electorales. Sin embargo, dicha evidencia aún no es generalizable y no hay consenso sobre la forma más adecuada de hacer analítica con datos de esta herramienta para este fin. El estudio examina si tales datos son útiles para predecir resultados de elecciones presidenciales, tomando como caso de estudio la elección de presidente de Colombia 2022-2026 (segunda vuelta), usando un marco reproducible propuesto de analítica descriptiva en R. Se tuvo una muestra de 1020 observaciones. Todos los escenarios de análisis (considerando Google, YouTube y ambos) acertaron respecto al candidato que fue elegido por los ciudadanos, siendo la mejor estimación aquella arrojada por los datos de un día antes de las elecciones: inferior de 2% de distancia respecto al verdadero porcentaje de votación de cada candidato. Esta propuesta es una alternativa costo-efectiva para predecir resultados de elecciones presidenciales.

Recent works have highlighted the relevance of Google Trends data for predicting electoral processes. However, the potential for the generalization of this evidence is still limited and there is still no consensus on the most appropriate method for performing analytics with data from this tool for this purpose. This study examines whether such data are useful for predicting presidential election results, taking as a case study the recent Colombian presidential election for 2022–2026, using a proposed reproducible framework of descriptive analytics in R. A sample of 1,020 observations was considered. All the analysis scenarios (considering Google, YouTube and both) were correct regarding the candidate who was finally elected by the citizens, and the best estimate was obtained by using data from one day before the election (less than 2% distance from the true result). This work is a cost-effective alternative for predicting presidential election results.

Referencias

Kugbonu, J.M., Total quality management practices and customer retention at Unity Rural Bank, PhD. Thesis, University of Cape Coast, Ghana, 2020.

Tourangeau, R., Cognitive science and survey methods: a cognitive perspective. In: Jabine, T., et al., Eds., Cognitive aspects of survey methodology: building a bridge between disciplines, National Academy Press, Washington DC, USA, 1984, pp. 73-100.

Cornesse, C. and Blom, A.G., Response quality in nonprobability and probability-based online panels. Sociological Methods & Research, pp. 1-30, 2020. DOI: https://doi.org/10.1177/0049124120914940

Daniel, S. Satisficing in survey design. Contemporary Approaches to Research in Mathematics, Science, Health and Environmental Education, pp. 1-5, 2012.

Holmes, E., Bourke, S. and Plumpton, C. Attitudes towards epilepsy in the UK population: results from a 2018 national survey. Seizure, 65, pp. 12-19, 2019. https://doi.org/10.1016/j.seizure.2018.12.012.

Hume, C., Enhancing questionnaire design through participant engagement to improve the outputs of evaluation, PhD. Thesis, University of Sunderland, England, 2017.

Krosnick, J.A., Response strategies for coping with the cognitive demands of attitude measures in surveys. Applied cognitive Psychology, 5(3), pp. 213-236, 1991. DOI: https://doi.org/10.1002/acp.2350050305

Arora, V.S., McKee, M. and Stuckler, D., Google Trends: Opportunities and limitations in health and health policy research. Health Policy, 123(3), pp. 338-341, 2019. DOI: https://doi.org/10.1016/j.healthpol.2019.01.001.

Connor, P., Sarafidis, V., Zyphur, M.J., Keltner, D. and Chen, S., Income inequality and White-on-Black racial bias in the United States: evidence from project implicit and Google Trends. Psychological Science, 30(2), pp. 205-222, 2019. DOI: https://doi.org/10.1177%2F0956797618815441.

Zattoni, F., Gül, M., Soligo, M. et al. The impact of COVID-19 pandemic on pornography habits: a global analysis of Google Trends. Int J Impot Res., 33, pp. 824-831, 2021. DOI: https://doi.org/10.1038/s41443-020-00380-w.

Registraduría Nacional del Estado Civil in Colombia. Elecciones presidenciales 2022, segunda Vuelta. [en línea]. Disponible en: https://www.registraduria.gov.co/ Leído el 19 de junio de 2022.

La República. Colombia se enfrenta a las elecciones más polarizadas que se recuerdan. Elecciones en Colombia, REPUBLICA/EP | [online]. Actualizado: 29.05.2022, 2022. [Fecha de consulta: June 18th of 2022]. Disponible en: https://www.republica.com/internacional/colombia-se-enfrenta-a-las-elecciones-mas-polarizadas-que-se-recuerdan-20220528-19251443782/.

El Comercio. Gustavo Petro vs. Rodolfo Hernández: ¿quién es favorito para ganar la segunda vuelta, según encuestas. EL COMERCIO RESPUESTAS/Elucidario. Redacción EC 16/06/2022, 2022. [en línea]. [Fecha de consulta: June 18th of 2022]. Disponible en: https://elcomercio.pe/respuestas/gustavo-petro-vs-rodolfo-hernandez-quien-es-el-favorito-de-la-segunda-vuelta-segun-encuestas-guarumo-y-econanalitica-rcn-yanhass-tdex-revtli-noticia/?ref=ecr.

Portafolio. Última encuesta: empate técnico con estrecha victoria de Hernández. ELECCIONES 2022, Junio 10 de 2022 - 09:43 A.M. [en línea]. [Fecha de consulta: June 19th of 2022]. Disponible en: https://www.portafolio.co/elecciones-2022/encuesta-invamer-hernandez-por-delante-de-petro-en-segunda-vuelta-566735.

Portafolio. Encuestas vs. elecciones: ¿atinaron o no al resultado?. ELECCIONES 2022 Junio 19 De 2022 - 11:34 P.M. [en línea]. [Fecha de consulta: June 20th of 2022]. Disponible en: https://www.portafolio.co/elecciones-2022/resultados-de-encuestas-presidenciales-2022-vs-resultados-finales-atinaron-o-no-gustavo-petro-567185.

Martínez-Martínez, P.J., Tendencias e interés por el sida/VIH en España: análisis de Google Trends. Revista Multidisciplinar del Sida, [en línea]. 8(20), pp. 33-45, 2020. Disponible en: https://www.sidastudi.org/resources/inmagic-img/DD64214.pdf.

Google. [Fecha de consulta: June 18th of 2022]. Ayuda de Google. Disponible en: https://support.google.com/trends/answer/4365533?hl=es&ref_topic=6248052.

Scharkow, M. and Vogelsgang, J., Measuring the public agenda using search engine queries. International Journal of Public Opinion Research, 23(1), pp. 104-113, 2011. DOI: https://doi.org/10.1093/ijpor/edq048.

Scheitle, C., Google’s insights for search: a note evaluating the use of search engine data in social research. Social Science Quarterly, 92(1), pp. 285-295, 2011. DOI: https://doi.org/10.1111/j.1540-6237.2011.00768.x.

Mavragani, A. and Tsagarakis, K.P., YES or NO: predicting the 2015 GReferendum results using Google Trends. Technological Forecasting & Social Change, Elsevier, 109(C), pp. 1-5, 2016. DOI: https://doi.org/10.1016/j.techfore.2016.04.028

Chai, S. and Sasaki, N., Using online tools to assess public responses to climate change mitigation policies in Japan. Future Internet, 3(2), pp. 117-129, 2011. DOI: https://doi.org/10.3390/fi3020117

Kaeserbauer, M., Hohenstatt, R. and Reed, R., Direct versus search engine traffic: an innovative approach to demand analysis in the property market. International Journal of Housing Markets and Analysis, 5(4), pp. 392-413, 2012. DOI: https://doi.org/10.1108/17538271211268538.

Mavragani, A. and Tsagarakis, G.O., Assessing the methods, tools, and statistical approaches in Google Trends research: systematic review. Journal of Medical Internet Research, 20(11), art. e270, 2018. DOI: https://doi.org/10.2196/jmir.9366

Vicente, M., Lopez-Menendez, A. and Perez, R., Forecasting unemployment with internet search data: does it help to improve prediction when job destruction is skyrocketing?. Technol. Forecast. Soc. Change, pp. 132-139, 2015. DOI: https://doi.org/10.1016/j.techfore.2014.12.005

Polykalas, S.E., Prezerakos, G.N. and Konidaris, A., An algorithm based on Google Trends’ data for future prediction. Case study: German Elections. In: IEEE International Symposium on Signal Processing and Information Technology, Athens, Greece, 2013, pp. 69-73, 2013. DOI: https://doi.org/10.1109/ISSPIT.2013.6781856

Prado-Román, C., Gómez-Martínez, R. and Orden-Cruz, C., Google Trends as a predictor of presidential elections: the United States versus Canada. American Behavioral Scientist,65(4), pp. 1-15, 2020. DOI: https://doi.org/10.1177%2F0002764220975067

Harkan, A.A. and Eriyanto A.A.H., Predicting the results of the 2019 Indonesian presidential election with Google Trends: analysis of accuracy, precision, and its opportunity. In: Proceedings of the Asia-Pacific Research in Social Sciences and Humanities Universitas Indonesia Conference (APRISH 2019). Series: Advances in Social Science, Education and Humanities Research, 2021. DOI: 10.2991/assehr.k.210531.001

Morsy, S., Dang, T.N., Kamel, M.G., Zayan, A.H., Makram, O.M., Elhady, M., Hirayama, K. and Huy, N.T., Prediction of Zika-confirmed cases in Brazil and Colombia using Google Trends. Epidemiology and Infection, 2018. DOI: https://doi.org/10.1017/S0950268818002078

Cómo citar

IEEE

[1]
J. I. Pérez-Rave, M. A. Maya-Restrepo, y F. González-Echavarría, «Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework», DYNA, vol. 90, n.º 225, pp. 64–70, mar. 2023.

ACM

[1]
Pérez-Rave, J.I., Maya-Restrepo, M.A. y González-Echavarría, F. 2023. Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework. DYNA. 90, 225 (mar. 2023), 64–70. DOI:https://doi.org/10.15446/dyna.v90n225.104189.

ACS

(1)
Pérez-Rave, J. I.; Maya-Restrepo, M. A.; González-Echavarría, F. Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework. DYNA 2023, 90, 64-70.

APA

Pérez-Rave, J. I., Maya-Restrepo, M. A. & González-Echavarría, F. (2023). Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework. DYNA, 90(225), 64–70. https://doi.org/10.15446/dyna.v90n225.104189

ABNT

PÉREZ-RAVE, J. I.; MAYA-RESTREPO, M. A.; GONZÁLEZ-ECHAVARRÍA, F. Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework. DYNA, [S. l.], v. 90, n. 225, p. 64–70, 2023. DOI: 10.15446/dyna.v90n225.104189. Disponível em: https://revistas.unal.edu.co/index.php/dyna/article/view/104189. Acesso em: 16 mar. 2026.

Chicago

Pérez-Rave, Jorge Iván, María Alejandra Maya-Restrepo, y Favián González-Echavarría. 2023. «Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework». DYNA 90 (225):64-70. https://doi.org/10.15446/dyna.v90n225.104189.

Harvard

Pérez-Rave, J. I., Maya-Restrepo, M. A. y González-Echavarría, F. (2023) «Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework», DYNA, 90(225), pp. 64–70. doi: 10.15446/dyna.v90n225.104189.

MLA

Pérez-Rave, J. I., M. A. Maya-Restrepo, y F. González-Echavarría. «Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework». DYNA, vol. 90, n.º 225, marzo de 2023, pp. 64-70, doi:10.15446/dyna.v90n225.104189.

Turabian

Pérez-Rave, Jorge Iván, María Alejandra Maya-Restrepo, y Favián González-Echavarría. «Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework». DYNA 90, no. 225 (marzo 3, 2023): 64–70. Accedido marzo 16, 2026. https://revistas.unal.edu.co/index.php/dyna/article/view/104189.

Vancouver

1.
Pérez-Rave JI, Maya-Restrepo MA, González-Echavarría F. Do Internet search patterns predict election results? An analysis of the 2022 presidential election in Colombia using a reproducible descriptive analytics framework. DYNA [Internet]. 3 de marzo de 2023 [citado 16 de marzo de 2026];90(225):64-70. Disponible en: https://revistas.unal.edu.co/index.php/dyna/article/view/104189

Descargar cita

CrossRef Cited-by

CrossRef citations1

1. Jorge Iván Pérez Rave, Rafael Fernández Guerrero, Andres Salas Vallina. (2024). Validation of a dispositional critical thinking scale using an original analytical methodology for addressing data from Google Trends. Baltic Journal of Management, 19(5), p.512. https://doi.org/10.1108/BJM-01-2024-0006.

Dimensions

PlumX

Visitas a la página del resumen del artículo

676

Descargas

Los datos de descargas todavía no están disponibles.