Laboratorio de la Conciencia, Instituto de Fisiolía, Biología Molecular y Neurociencia. Buenos Aires, Argentina
Universidad de Buenos Aires, Facultad de Psicología. Buenos Aires, Argentina
Universidad de Buenos Aires, Instituto de las Ciencias de la Computación. Buenos Aires, Argentina
Universidad de Buenos Aires, Instituto de las Ciencias de la Computación. Buenos Aires, Argentina
Laboratorio de la Conciencia, Instituto de Fisiolía, Biología Molecular y Neurociencia. Buenos Aires, Argentina
Text sentiment analysis is a valuable tool in natural language processing, allowing the inference of emotional valuations in texts. Initially designed for English tweets, we have adapted these algorithms to analyze Spanish news headlines 1. During the 2019 election, major candidates received increased media attention and were the subject of more positive coverage 2. In our current study, we analyzed 12,059 news headlines published by mainstream media during the 2023 election. We observed that 58.35% of the headlines mentioned Milei, followed by 29.54% Massa, and 10.76% Bullrich, while Bregman and Schiaretti had a lower presence. We excluded the latter from the analysis due to their low support. The Kruskal-Wallis analysis showed significant differences in mean positivity among the remaining candidates (H=10.63; p<0.005), especially between Bullrich-Milei (p<0.04) and Massa-Milei (p<0.0001). For the ballotage, the mean positivity of Milei and Massa was almost significant (p<0.057). A time series analysis revealed an increase in positivity towards Massa before the general election, but positivity towards Milei predominated before the ballotage. Although social networks are the main platform to disseminate libertarian ideas associated with Milei, the press media have favored his candidacy (along with Bullrich), establishing a common right-wing political agenda. This is reflected in the mentions and positivity associated with the libertarian candidate, suggesting a significant influence of the media in the public perception of the candidates during the electoral process
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.