Printed Media and Artificial Intelligence
Sentiment Analysis of News about the Workers' Party in Ponta Grossa, PR, Brazil, in the 1980s
DOI:
https://doi.org/10.5212/TerraPlural.v.16.2220989.042Keywords:
Print Newspapers, Worker's Party, Syuzhet, Sentiment AnalysisAbstract
This paper aims to understand how the news in newspapers referring to the Workers’ Party (PT) in Ponta Grossa in the 1980s can be understood through Sentiment Analysis. In this sense, the journalistic publications of a certain spatial and temporal cut are analyzed, with the use of opinion mining techniques applying artificial intelligence to decipher aspects of natural language. We used the Syuzhet package included in Rbase, through the Rstudio interface, where we could verify that the positive emotions and feelings transmitted by the news published during the time under analysis, contributed to the electoral adhesion to the PT, electing members in the legislative and executive branches of the municipal government, a situation that had its share of influence in later decades in other spheres of the State. In this paper we try to make clear the path is taken to reach our results, allowing the methodology to be applied to other printed periodicals and other themes.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Ricardo Enguel Gonçalves, João Paulo Leandro Almeida
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Revista Terr@ Plural will obtain the auctorial rights for all published texts. This also implies that the text can be published anywhere in the world, including all rights on renewal, expansion, and dissemination of the contribution, as well as other subsidiary rights. The authors get permission to publish the contribution in other media, printed or digital, it may be in Portuguese or translation since the publication is credited to Revista Terr@ Plural. It allows the self-archiving of published articles in institutional repositories, thematic repositories, or personal web pages in the pdf version downloaded from the journal's site.
