Cultura política y polaridad electoral en España, a través de Twitter. (Spanish)

The work seeks to understand Twitter's political incidents in the type of political culture and the polarity of opinions promoted by the leading Spanish political groups in the last three electoral processes in Spain (2016 and 2019). The paper does a topic analysis, extracted from the messages published by the cases studied, applying topic modeling techniques using machine learning through the Latent Dirichlet Allocation (LDA) algorithm. The study shows how the main Spanish political groups use asymmetric communication strategies on Twitter, highly polarized, concentrated on confrontation with opponents, and promoting a discursive political culture focused on abstract and general meanings, looking for credibility electoral scenario studied. [ABSTRACT FROM AUTHOR]

El trabajo busca comprender la incidencia política de Twitter en el tipo de cultura política y la polaridad de opiniones promovidas por los principales grupos políticos españoles en los últimos tres procesos electorales en España (2016 y 2019). Para ello se lleva a cabo un análisis de tópicos, extraídos de los mensajes publicados por los casos estudiados, aplicando técnicas de modelado de temas mediante machine learning, a través del algoritmo Latent Dirichlet Allocation (LDA). El estudio muestra cómo los principales grupos políticos españoles emplean unas estrategias de comunicación asimétricas en Twitter, muy polarizados y centrados en la confrontación con los oponentes y la promoción de una cultura política fundamentada discursivamente en significados abstractos y generales, empleados para diferenciar y dotarse de credibilidad en el escenario electoral estudiado. [ABSTRACT FROM AUTHOR]

Copyright of Estudos em Comunicação is the property of Labcom / Universidade da Beira Interior and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)