Large-scale and long-term characterization of political communications on social media
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/36669 |
Resumo: | Social media play an important role in shaping political discourse, creating a public sphere that enables discussions, debates, and deliberations. Aware of this importance, politicians use social media for self-promotion and as a means of influencing people and votes. As an example of this assertion, in 2018, Brazilians democratically elected for president the far-right candidate Jair Bolsonaro. One of the most surprising feats of this outcome is that his party, PSL, had almost no television time. His victory was only possible because of his supporters’ engagement and activism on social media platforms, such as on Twitter, Facebook, and WhatsApp. In this context, politicians need to decide how to communicate with their voters to build their reputations. While some politicians only share professional communi- cations about their political agenda and activities, others prefer a more non-political and informal approach, sharing communications about the most varied subjects, such as religion, sports, and their families. Others, however, misuse platforms by spreading political messages that violate policies and circumvent electoral laws. Aware of these problems, we propose a supervised machine learning classifier that labels all textual messages from different social media platforms as political and non- political. The classifier runs on a large scale and it is robust to concept drifts over time, requiring few new labeled messages each year. From the classified messages, we were able to characterize the communication of politicians over time and identified new findings: (i) Brazilian congresspeople changed their communication behavior over time; (ii) concept drifts occurred during important events of Brazilian politics; (iii) the explosive rise of the right seen just before the 2018 elections; (iv) a broader and more evenly distributed right-wing participation than the left-wing, and, finally, (v) the increase of public engagement over time. |
id |
UFMG_4cbe12a225a7ec9b8d5888fd965dded8 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/36669 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Pedro Olmo Stancioli Vaz de Melohttp://lattes.cnpq.br/3262926164579789Jussara Marques de Almeda GonçalvesFabrício Benevenuto de SouzaAline Carneiro VianaArtur ZivianiAline Marins Paes Carvalhohttp://lattes.cnpq.br/3965923523593288Lucas Santos de Oliveira2021-07-07T00:37:32Z2021-07-07T00:37:32Z2021-02-09http://hdl.handle.net/1843/36669Social media play an important role in shaping political discourse, creating a public sphere that enables discussions, debates, and deliberations. Aware of this importance, politicians use social media for self-promotion and as a means of influencing people and votes. As an example of this assertion, in 2018, Brazilians democratically elected for president the far-right candidate Jair Bolsonaro. One of the most surprising feats of this outcome is that his party, PSL, had almost no television time. His victory was only possible because of his supporters’ engagement and activism on social media platforms, such as on Twitter, Facebook, and WhatsApp. In this context, politicians need to decide how to communicate with their voters to build their reputations. While some politicians only share professional communi- cations about their political agenda and activities, others prefer a more non-political and informal approach, sharing communications about the most varied subjects, such as religion, sports, and their families. Others, however, misuse platforms by spreading political messages that violate policies and circumvent electoral laws. Aware of these problems, we propose a supervised machine learning classifier that labels all textual messages from different social media platforms as political and non- political. The classifier runs on a large scale and it is robust to concept drifts over time, requiring few new labeled messages each year. From the classified messages, we were able to characterize the communication of politicians over time and identified new findings: (i) Brazilian congresspeople changed their communication behavior over time; (ii) concept drifts occurred during important events of Brazilian politics; (iii) the explosive rise of the right seen just before the 2018 elections; (iv) a broader and more evenly distributed right-wing participation than the left-wing, and, finally, (v) the increase of public engagement over time.As mídias sociais desempenham um papel importante na formação do discurso político, criando uma esfera pública que possibilita discussões, debates e deliberações. Cientes dessa importância, os políticos utilizam as redes sociais para se autopromoverem e como forma de influenciar pessoas e votos. Como exemplo dessa afirmação, em 2018, os brasileiros elegeram democraticamente para presidente o candidato Jair Bolsonaro. Um dos feitos mais surpreendentes desse desfecho é que seu partido, o PSL, quase não teve tempo de televisão. Sua vitória só foi possível devido ao engajamento e ao ativismo de seus apoiadores nas plataformas de mídias sociais, como Twitter, Facebook e WhatsApp. Nesse contexto, os políticos precisam decidir como se comunicarem com seus eleitores para construirem suas reputações. Enquanto alguns políticos compartilham apenas comunicações profissionais sobre suas agendas e atividades políticas, outros preferem uma abordagem não-política e informal, compartilhando comunicações sobre os mais diversos assuntos, como religião, esportes e família. Outros, no entanto, fazem mau uso das plataformas, espalhando mensagens políticas que violam os termos e condições de uso das redes sociais e as leis eleitorais. Ciente desses problemas, propomos um classificador supervisionado baseado em aprendizado de máquina que rotula todas as mensagens textuais de diferentes plataformas de mídias sociais como políticas e não políticas. O classificador é utilizado em larga escala e é robusto a mudanças de conceito ao longo do tempo, exigindo poucas novas mensagens rotuladas a cada ano. A partir das mensagens classificadas, pudemos caracterizar as comunicações dos políticos ao longo do tempo e fazer novas descobertas: (i) os parlamentares brasileiros mudaram seus comportamentos de comunicação ao longo do tempo; (ii) mudanças de conceito ocorreram durante eventos importantes da política brasileira; (iii) uma ascen são explosiva da direita vista pouco antes do Eleições de 2018; (iv) uma participação da direita mais ampla e mais bem distribuída do que a da esquerda e, por fim, (v) o aumento do engajamento do público ao longo do tempo.Outra AgênciaengUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOhttp://creativecommons.org/licenses/by-nc/3.0/pt/info:eu-repo/semantics/openAccessComputação – TesesMídias sociais – TesesRedes sociais on-line – TesesRedes sociais on-line – Aspectos políticos – TesesPoliticalSocial mediaCommunicationCharacterizationLarge-scale and long-term characterization of political communications on social mediaCaracterização em larga escala e a longo prazo de comunicações políticas nas mídias sociaisinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGLICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/36669/5/license.txtcda590c95a0b51b4d15f60c9642ca272MD55ORIGINALtese_sem_folhas_branco.pdftese_sem_folhas_branco.pdfapplication/pdf7874050https://repositorio.ufmg.br/bitstream/1843/36669/4/tese_sem_folhas_branco.pdfad9dedb1502c672260008dab831fae76MD54CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8920https://repositorio.ufmg.br/bitstream/1843/36669/2/license_rdf33b8016dc5c4681c1e7a582a4161162cMD521843/366692021-07-06 21:37:32.717oai:repositorio.ufmg.br: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ório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2021-07-07T00:37:32Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
Large-scale and long-term characterization of political communications on social media |
dc.title.alternative.pt_BR.fl_str_mv |
Caracterização em larga escala e a longo prazo de comunicações políticas nas mídias sociais |
title |
Large-scale and long-term characterization of political communications on social media |
spellingShingle |
Large-scale and long-term characterization of political communications on social media Lucas Santos de Oliveira Political Social media Communication Characterization Computação – Teses Mídias sociais – Teses Redes sociais on-line – Teses Redes sociais on-line – Aspectos políticos – Teses |
title_short |
Large-scale and long-term characterization of political communications on social media |
title_full |
Large-scale and long-term characterization of political communications on social media |
title_fullStr |
Large-scale and long-term characterization of political communications on social media |
title_full_unstemmed |
Large-scale and long-term characterization of political communications on social media |
title_sort |
Large-scale and long-term characterization of political communications on social media |
author |
Lucas Santos de Oliveira |
author_facet |
Lucas Santos de Oliveira |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Pedro Olmo Stancioli Vaz de Melo |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/3262926164579789 |
dc.contributor.referee1.fl_str_mv |
Jussara Marques de Almeda Gonçalves |
dc.contributor.referee2.fl_str_mv |
Fabrício Benevenuto de Souza |
dc.contributor.referee3.fl_str_mv |
Aline Carneiro Viana |
dc.contributor.referee4.fl_str_mv |
Artur Ziviani |
dc.contributor.referee5.fl_str_mv |
Aline Marins Paes Carvalho |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/3965923523593288 |
dc.contributor.author.fl_str_mv |
Lucas Santos de Oliveira |
contributor_str_mv |
Pedro Olmo Stancioli Vaz de Melo Jussara Marques de Almeda Gonçalves Fabrício Benevenuto de Souza Aline Carneiro Viana Artur Ziviani Aline Marins Paes Carvalho |
dc.subject.por.fl_str_mv |
Political Social media Communication Characterization |
topic |
Political Social media Communication Characterization Computação – Teses Mídias sociais – Teses Redes sociais on-line – Teses Redes sociais on-line – Aspectos políticos – Teses |
dc.subject.other.pt_BR.fl_str_mv |
Computação – Teses Mídias sociais – Teses Redes sociais on-line – Teses Redes sociais on-line – Aspectos políticos – Teses |
description |
Social media play an important role in shaping political discourse, creating a public sphere that enables discussions, debates, and deliberations. Aware of this importance, politicians use social media for self-promotion and as a means of influencing people and votes. As an example of this assertion, in 2018, Brazilians democratically elected for president the far-right candidate Jair Bolsonaro. One of the most surprising feats of this outcome is that his party, PSL, had almost no television time. His victory was only possible because of his supporters’ engagement and activism on social media platforms, such as on Twitter, Facebook, and WhatsApp. In this context, politicians need to decide how to communicate with their voters to build their reputations. While some politicians only share professional communi- cations about their political agenda and activities, others prefer a more non-political and informal approach, sharing communications about the most varied subjects, such as religion, sports, and their families. Others, however, misuse platforms by spreading political messages that violate policies and circumvent electoral laws. Aware of these problems, we propose a supervised machine learning classifier that labels all textual messages from different social media platforms as political and non- political. The classifier runs on a large scale and it is robust to concept drifts over time, requiring few new labeled messages each year. From the classified messages, we were able to characterize the communication of politicians over time and identified new findings: (i) Brazilian congresspeople changed their communication behavior over time; (ii) concept drifts occurred during important events of Brazilian politics; (iii) the explosive rise of the right seen just before the 2018 elections; (iv) a broader and more evenly distributed right-wing participation than the left-wing, and, finally, (v) the increase of public engagement over time. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-07-07T00:37:32Z |
dc.date.available.fl_str_mv |
2021-07-07T00:37:32Z |
dc.date.issued.fl_str_mv |
2021-02-09 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/doctoralThesis |
format |
doctoralThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/1843/36669 |
url |
http://hdl.handle.net/1843/36669 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/3.0/pt/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/3.0/pt/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.publisher.program.fl_str_mv |
Programa de Pós-Graduação em Ciência da Computação |
dc.publisher.initials.fl_str_mv |
UFMG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
ICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃO |
publisher.none.fl_str_mv |
Universidade Federal de Minas Gerais |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFMG instname:Universidade Federal de Minas Gerais (UFMG) instacron:UFMG |
instname_str |
Universidade Federal de Minas Gerais (UFMG) |
instacron_str |
UFMG |
institution |
UFMG |
reponame_str |
Repositório Institucional da UFMG |
collection |
Repositório Institucional da UFMG |
bitstream.url.fl_str_mv |
https://repositorio.ufmg.br/bitstream/1843/36669/5/license.txt https://repositorio.ufmg.br/bitstream/1843/36669/4/tese_sem_folhas_branco.pdf https://repositorio.ufmg.br/bitstream/1843/36669/2/license_rdf |
bitstream.checksum.fl_str_mv |
cda590c95a0b51b4d15f60c9642ca272 ad9dedb1502c672260008dab831fae76 33b8016dc5c4681c1e7a582a4161162c |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG) |
repository.mail.fl_str_mv |
|
_version_ |
1803589496652955648 |