Measuring the performances of politicians on social media and the correlation with major Latin American election results

Abstract

Contemporary social media (SM) has strongly impacted democratic practices. The success of presidential campaigns is frequently attributed to being highly correlated with the candidates' social media performance, but there is no well-established method to measure this performance. Thus, this study aims to improve the understanding of a politician's performance on SM and its correlation with electoral results. Applying a new, recently-defined set of metrics, based on Zajonc's exposition theory and considering the interactions of users on politicians' profiles in multiple SM platforms, this research identifies statistical correlations between SM performance and the votes received in multiple elections. As case studies, this paper focuses on the most recent presidential elections in the four most populous countries in Latin America: Argentina (2019), Brazil (2018), Colombia (2018), and Mexico (2018). Data from more than 65,000 posts were collected from the SM profiles of the main candidates on Facebook, Twitter, and Instagram, starting from 300 days before the election days, and correlations with electoral results were calculated. The results demonstrated strong correlations between the defined metrics and the votes received, particularly the engagement per post, although there were differences among countries. On the other hand, we observed that there is zero or negative correlation between the number of posts and the electoral results.