Analyzing parliamentary elections based on voting advice application data

  • Authors:

  • Jaakko Talonen;Mika Sulkava

  • Affiliations:

  • Aalto University School of Science, Department of Information and Computer Science, Aalto, Finland;Aalto University School of Science, Department of Information and Computer Science, Aalto, Finland

  • Venue:
  • IDA'11 Proceedings of the 10th international conference on Advances in intelligent data analysis X
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The main goal of this paper is to model the values of Finnish citizens and the members of the parliament. To achieve this goal, two databases are combined: voting advice application data and the results of the parliamentary elections in 2011. First, the data is converted to a high-dimension space. Then, it is projected to two principal components. The projection allows us to visualize the main differences between the parties. The value grids are produced with a kernel density estimation method without explicitly using the questions of the voting advice application. However, we find meaningful interpretations for the axes in the visualizations with the analyzed data. Subsequently, all candidate value grids are weighted by the results of the parliamentary elections. The result can be interpreted as a distribution grid for Finnish voters' values.