Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election

Detalhes bibliográficos
Autor(a) principal: Costa, Felipe Soares
Data de Publicação: 2023
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/152308
Resumo: Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
id RCAP_e3c49770fd1130da90c53cf49f5fd65d
oai_identifier_str oai:run.unl.pt:10362/152308
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential ElectionPolitical PolarizationSentiment AnalysisNatural Language ProcessingTopic ModelingProject Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data ScienceSocial Media has become a big part of our society and has now a significant role in the relationships between inter and intra-communities. Twitter is now an important communication platform for political campaigns: in the last years, politicians, campaigners, and general users have been extensively using Twitter to promote campaigns and engage in political discussions. Some studies argue that social media can create filter bubbles by limiting the flow of online information, and therefore creating communities where exposure to political diversity is rare. This selective exposure can build echo chambers where individuals only interact with those who have the same opinions as they have and by doing that, they build a polarized community. Identifying, understanding, and mitigating polarization is very important for the democratic process. People should be exposed to different ideas and opinions so they can choose their representatives without being influenced by some portion of the information. This project analyzed political polarization on social media using data from Twitter. Brazil’s presidential election in 2022 was used as a case study. Tweets from the two main candidates were extracted. A Topic Modeling algorithm was used to cluster tweets in topics. An Engagement Graph was built based on the interactions between users, candidates, and topics and was used to compute the Topic Centrality measures. A pre-trained Sentiment Analysis model was used to measure the sentiment polarity of each tweet. In the end, the project analyzed the extracted features and identified which topics were more central to each candidate and how users interact with them. The major conclusion of this work is that polarization in Brazil is more affective than ideological since the user’s sentiments towards topics are not as relevant as the sentiments towards the candidates.Henriques, Roberto André PereiraRUNCosta, Felipe Soares2023-05-02T10:52:40Z2023-04-132023-04-13T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/152308TID:203273311enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:34:37Zoai:run.unl.pt:10362/152308Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:54:51.315683Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
title Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
spellingShingle Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
Costa, Felipe Soares
Political Polarization
Sentiment Analysis
Natural Language Processing
Topic Modeling
title_short Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
title_full Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
title_fullStr Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
title_full_unstemmed Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
title_sort Analyzing Polarization on Social Media: A Case Study of the 2022 Brazil Presidential Election
author Costa, Felipe Soares
author_facet Costa, Felipe Soares
author_role author
dc.contributor.none.fl_str_mv Henriques, Roberto André Pereira
RUN
dc.contributor.author.fl_str_mv Costa, Felipe Soares
dc.subject.por.fl_str_mv Political Polarization
Sentiment Analysis
Natural Language Processing
Topic Modeling
topic Political Polarization
Sentiment Analysis
Natural Language Processing
Topic Modeling
description Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science
publishDate 2023
dc.date.none.fl_str_mv 2023-05-02T10:52:40Z
2023-04-13
2023-04-13T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/152308
TID:203273311
url http://hdl.handle.net/10362/152308
identifier_str_mv TID:203273311
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138136642551808