Indexed in

License and use

Citations

Cited 20 times in

Cited 15 times in

Cited 17 times in

Altmetrics

Grant support

This work was supported in part by the KLINILYCS under Grant TEC2016-75361-R, in part by the AAVis-BMR under Grant PID2019-107768RA-I00, in part by the BigTheory under Grant PID2019-106623RB-C41, in part by the meHeart RisBi under Grant PID2019-104356RB-C42, in part by the miHeart-DaBa through the Agencia Estatal de Investigacion and co-funded by FEDER under Grant PID2019-104356RB-C43, in part by the Young Researchers Research and Development Project through the Community of Madrid and Rey Juan Carlos University under Project 2020-656, in part by the KERMES under Grant TEC2016-81900-REDT, and in part by the MAPAS through the Spanish Government under Grant TIN2017-90567-REDT.

Analysis of institutional authors

Share

Sentiment Analysis of Political Tweets From the 2019 Spanish Elections

Publicated to:Ieee Access. 9 101847-101862 - 2021-01-01 9(), DOI: 10.1109/ACCESS.2021.3097492

Authors: Rodriguez-Ibanez, Margarita; Gimeno-Blanes, Francisco-Javier; Cuenca-Jimenez, Pedro Manuel; Soguero-Ruiz, Cristina; Rojo-Alvarez, Jose Luis

Affiliations

Abstract

The use of sentiment analysis methods has increased in recent years across a wide range of disciplines. Despite the potential impact of the development of opinions during political elections, few studies have focused on the analysis of sentiment dynamics and their characterization from statistical and mathematical perspectives. In this paper, we apply a set of basic methods to analyze the statistical and temporal dynamics of sentiment analysis on political campaigns and assess their scope and limitations. To this end, we gathered thousands of Twitter messages mentioning political parties and their leaders posted several weeks before and after the 2019 Spanish presidential election. We then followed a twofold analysis strategy: (1) statistical characterization using indices derived from well-known temporal and information metrics and methods -including entropy, mutual information, and the Compounded Aggregated Positivity Index- allowing the estimation of changes in the density function of sentiment data; and (2) feature extraction from nonlinear intrinsic patterns in terms of manifold learning using autoencoders and stochastic embeddings. The results show that both the indices and the manifold features provide an informative characterization of the sentiment dynamics throughout the election period. We found measurable variations in sentiment behavior and polarity across the political parties and their leaders and observed different dynamics depending on the parties' positions on the political spectrum, their presence at the regional or national levels, and their nationalist or globalist aspirations.

Keywords