Clusterización electoral de los municipios de Antioquia mediante algoritmo de clasificación no supervisada K-Means

José Sebastian Díaz-Arguello

doi:10.33571/rpolitec.v21n42a6

Authors

José Sebastian Díaz-Arguello Politécnico Jaime Isaza Cadavid https://orcid.org/0009-0007-9995-9674

DOI:

https://doi.org/10.33571/rpolitec.v21n42a6

Keywords:

Electoral, Democracy, Politics, Clustering, Statistics

Abstract

This study aims to classify the municipalities of the department of Antioquia according to their electoral behavior in the 2022 Senate elections, through the application of the unsupervised classification algorithm K-Means. Political parties with a participation greater than 5% of the total votes in the department were selected. The results allowed the identification of four clústers with clear electoral patterns: one with a predominant liberal tendency, another showing a balanced distribution among parties, a group oriented toward the Centro Democrático party, and a group with a conservative predominance. The methodology proved effective in detecting territorial electoral patterns, demonstrating the usefulness of machine learning techniques in electoral analysis and their potential application in comparative political studies.

Article Metrics

Abstract: 31 PDF (Español (España)): 14

PlumX metrics

Author Biography

José Sebastian Díaz-Arguello, Politécnico Jaime Isaza Cadavid

Economista y Magister en Ciencias Económicas de la universidad Santo Tomas, Especialista en Analítica de datos del Politécnico Jaime Isaza Cadavid

References

[1] S. Lloyd, “Least Squares Quantization in PCM,” IEEE Transactions on Information Theory, vol. 28, no. 2, pp. 129–137, 1982. doi: 10.1109/TIT.1982.1056489.

[2] P. Nietto, M. Nicoletti, and N. Sacco, “Analyzing Electoral Data Using Partitional and Hierarchical Clustering Algorithms,” in Intelligent Systems Design and Applications, 2022. doi: 10.1007/978-3-031-27440-4_6.

[3] Y.-C. Hung and L.-Y. Chen, “Using Intelligent Clustering to Implement Geometric Computation for Electoral Districting,” International Journal of Geo-Information, vol. 8, no. 9, 2019. doi: 10.3390/ijgi8090369.

[4] C. J. Perdomo, “¿Se pueden predecir geográficamente los resultados electorales?,” Estudios Demográficos y Urbanos, vol. 23, no. 3, 2008. doi: 10.24201/edu.v23i3.1322.

[5] Y. Nesterov, “Soft clustering by convex electoral model,” Soft Computing, vol. 24, 2020. doi: 10.1007/s00500-020-05148-4.

[6] L. Kotthoff, B. O’Sullivan, S. Ravi, and I. Davidson, “Complex Clustering Using Constraint Programming: Modelling Electoral Map Creation,” unpublished manuscript, 2015.

[7] Y. Photis, “Redefinition of the Greek Electoral Districts through the Application of a Region-Building Algorithm,” European Journal of Geography, vol. 3, no. 2, 2012.

[8] A. Brieden, P. Gritzmann, and F. Klemm, “Constrained Clustering via Diagrams: A Unified Theory and Its Application to Electoral District Design,” European Journal of Operational Research, vol. 263, no. 1, 2017. doi: 10.1016/j.ejor.2017.04.018.

[9] T. Kodinariya and P. Makwana, “Review on Determining of Cluster in K-means Clustering,” International Journal of Advance Research in Computer Science and Management Studies, vol. 1, no. 6, 2013.

[10] P. Rousseeuw, “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis,” Journal of Computational and Applied Mathematics, vol. 20, pp. 53–65, 1987. doi: 10.1016/0377-0427(87)90125-7.

[11] A. K. Jain, “Data clustering: 50 years beyond K-means,” Pattern Recognition Letters, vol. 31, no. 8, pp. 651–666, 2010. doi: 10.1016/j.patrec.2009.09.011.