Machine learning for nowcasting elections in Latin America based on social media engagement and polls
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Tese |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFPE |
Texto Completo: | https://repositorio.ufpe.br/handle/123456789/40462 |
Resumo: | Contemporary social media (SM) represents a new communication paradigm and has impacted politics and electoral campaigns. The mobilization of the Arab Spring social movements was attributed to SM platforms, as well as successful electoral campaigns such as those of Obama and Trump in the U.S. (2008, 2012, and 2016), the Brexit campaign in 2016, and the Bolsonaro campaign for the Brazilian presidency in 2018. Within this new scenario, the advantages of collecting SM data over traditional polling methods include the huge volume of available data, the high speed, and low costs. Hence, researchers are endeavoring to discover how to use SM for nowcasting election results. However, despite the alleged success, the most-common approach, based on counting the volume of mentions on Twitter and conducting a sentiment analysis, has been frequently criticized and challenged. On the other hand, recent approaches based on other SM platforms and on the advances of machine learning (ML) may be promising alternatives. In this context, this thesis aims to advance the state-of-the-art on predicting elections based on SM data. It proposes a new set of SM performance metrics to be input features for the ML techniques by changing the focus onto the number of people paying attention to the candidates. The defined metrics may be used not only with the most commonly-used current SM platforms (i.e., Facebook, Instagram, and Twitter) but even with future platforms which have not yet gained popularity. In addition, this thesis defines SoMEN, the Social Media framework for Election Nowcasting, a framework composed of a process and model for nowcasting election results based on the SM performance features and using ML approaches. It proposes well-defined steps, ranging from election understanding to prediction evaluation, and an ML model for predicting the final election results based on an ensemble of artificial neural networks (ANN) trained with SM metrics as features and offline polls as labeled data. It also defines SoMEN-DC, an execution strategy for SoMEN that enables continuous prediction during the campaign (DC). The proposed metrics and framework were applied on the most recent main presidential elections in Latin America: Argentina (2019), Brazil (2018), Colombia (2018), and Mexico (2018). More than 65,000 posts were collected from the SM profiles on Facebook, Twitter, and Instagram of the candidates, as well as data from 195 presidential polls. Results demonstrated that the defined metrics presented a high correlation with the final share of votes in all the studied countries. Moreover, it was also possible to achieve a high level of accuracy in predicting the final vote share of the candidates, with competitive or better results than traditional polls. Lastly, despite the difficulty in measuring the quality of predictions during the campaign, results are promising and also competitive to polls. The strategies put forward in this thesis have attempted to handle several among the current challenges in this research area and indicate a new manner on how to face the problems. Furthermore, they may be directly used for nowcasting future elections in similar scenarios. |
id |
UFPE_8dc2825d7ede7a56ab2d167357c0812a |
---|---|
oai_identifier_str |
oai:repositorio.ufpe.br:123456789/40462 |
network_acronym_str |
UFPE |
network_name_str |
Repositório Institucional da UFPE |
repository_id_str |
2221 |
spelling |
BRITO, Kellyton dos Santoshttp://lattes.cnpq.br/8750956715158540http://lattes.cnpq.br/3524590211304012ADEODATO, Paulo Jorge Leitão2021-07-08T19:46:43Z2021-07-08T19:46:43Z2021-03-18BRITO, Kellyton dos Santos. Machine learning for nowcasting elections in Latin America based on social media engagement and polls. 2021. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2021.https://repositorio.ufpe.br/handle/123456789/40462Contemporary social media (SM) represents a new communication paradigm and has impacted politics and electoral campaigns. The mobilization of the Arab Spring social movements was attributed to SM platforms, as well as successful electoral campaigns such as those of Obama and Trump in the U.S. (2008, 2012, and 2016), the Brexit campaign in 2016, and the Bolsonaro campaign for the Brazilian presidency in 2018. Within this new scenario, the advantages of collecting SM data over traditional polling methods include the huge volume of available data, the high speed, and low costs. Hence, researchers are endeavoring to discover how to use SM for nowcasting election results. However, despite the alleged success, the most-common approach, based on counting the volume of mentions on Twitter and conducting a sentiment analysis, has been frequently criticized and challenged. On the other hand, recent approaches based on other SM platforms and on the advances of machine learning (ML) may be promising alternatives. In this context, this thesis aims to advance the state-of-the-art on predicting elections based on SM data. It proposes a new set of SM performance metrics to be input features for the ML techniques by changing the focus onto the number of people paying attention to the candidates. The defined metrics may be used not only with the most commonly-used current SM platforms (i.e., Facebook, Instagram, and Twitter) but even with future platforms which have not yet gained popularity. In addition, this thesis defines SoMEN, the Social Media framework for Election Nowcasting, a framework composed of a process and model for nowcasting election results based on the SM performance features and using ML approaches. It proposes well-defined steps, ranging from election understanding to prediction evaluation, and an ML model for predicting the final election results based on an ensemble of artificial neural networks (ANN) trained with SM metrics as features and offline polls as labeled data. It also defines SoMEN-DC, an execution strategy for SoMEN that enables continuous prediction during the campaign (DC). The proposed metrics and framework were applied on the most recent main presidential elections in Latin America: Argentina (2019), Brazil (2018), Colombia (2018), and Mexico (2018). More than 65,000 posts were collected from the SM profiles on Facebook, Twitter, and Instagram of the candidates, as well as data from 195 presidential polls. Results demonstrated that the defined metrics presented a high correlation with the final share of votes in all the studied countries. Moreover, it was also possible to achieve a high level of accuracy in predicting the final vote share of the candidates, with competitive or better results than traditional polls. Lastly, despite the difficulty in measuring the quality of predictions during the campaign, results are promising and also competitive to polls. The strategies put forward in this thesis have attempted to handle several among the current challenges in this research area and indicate a new manner on how to face the problems. Furthermore, they may be directly used for nowcasting future elections in similar scenarios.As redes sociais contemporâneas representam um novo paradigma de comunicação e têm impactado a política e as campanhas eleitorais. A mobilização dos movimentos sociais da Primavera Árabe foi atribuída às redes sociais, assim como o sucesso de campanhas eleitorais como as de Obama e Trump nos Estados Unidos (2008, 2012 e 2016), o Brexit em 2016, e a campanha de Bolsonaro no Brasil em 2018. Neste novo cenário, as vantagens de coletar os dados das redes sociais sobre os métodos de pesquisa eleitoral tradicionais incluem a grande quantidade de dados disponíveis, a alta velocidade e baixo custo de coleta. Consequentemente, pesquisas estão sendo realizadas para usar as redes para prever os resultados eleitorais. Apesar do suposto sucesso da abordagem mais comum, baseada na contagem do volume de menções no Twitter combinada com análise de sentimento, esta tem sido frequentemente criticada e contestada. Por outro lado, novas abordagens baseadas em outras redes e nos avanços do aprendizado de máquina podem ser alternativas promissoras. Nesse contexto, esta tese objetiva avançar o estado da arte na previsão de eleições baseada em dados das redes sociais. Ela propõe um novo conjunto de métricas de desempenho nas redes, mudando o foco para o número de pessoas prestando atenção aos candidatos. As métricas definidas podem ser usadas tanto com as redes sociais mais populares atualmente (Facebook, Instagram e Twitter), quanto com plataformas futuras que ainda não ganharam popularidade. Esta tese também define o SoMEN (Social Media framework for Election Nowcasting), um framework composto por um processo e modelo para previsão das eleições baseado no desempenho nas redes sociais e usando abordagens de aprendizado de máquina. Ele propõe etapas bem definidas, que vão desde o entendimento da eleição até a avaliação das previsões, e um modelo para prever os resultados finais da eleição com base em um conjunto (ensemble) de redes neurais artificiais treinadas com as novas métricas de performance como variáveis e as pesquisas tradicionais como dados rotulados. Também definimos a SoMEN-DC, uma estratégia de execução para o SoMEN que permite a previsão contínua durante a campanha (DC). As métricas e o framework proposto foram aplicados nas principais eleições presidenciais mais recentes na América Latina: Argentina (2019), Brasil (2018), Colômbia (2018) e México (2018). Mais de 65.000 posts foram coletados dos perfis dos candidatos no Facebook, Twitter e Instagram, bem como dados de 195 pesquisas eleitorais. Os resultados demonstraram que as métricas definidas apresentaram alta correlação com o percentual de votos obtido pelos candidatos em todos os países estudados. Além disso, foi obtido um alto nível de precisão na previsão do percentual final de votos dos candidatos, com resultados competitivos ou melhores do que as pesquisas tradicionais. Por fim, apesar da dificuldade em medir a qualidade das previsões durante a campanha, os resultados são promissores e competitivos com as pesquisas. As estratégias propostas nesta tese levaram em consideração os principais desafios desta área de pesquisa e apresentam uma nova maneira de enfrentá-los. Além disso, elas podem ser usadas diretamente para prever eleições futuras em cenários semelhantes.engUniversidade Federal de PernambucoPrograma de Pos Graduacao em Ciencia da ComputacaoUFPEBrasilAttribution-NonCommercial-NoDerivs 3.0 Brazilhttp://creativecommons.org/licenses/by-nc-nd/3.0/br/info:eu-repo/semantics/openAccessInteligência ComputacionalRedes sociaisEleiçõesAprendizado de máquinasMachine learning for nowcasting elections in Latin America based on social media engagement and pollsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/doctoralThesisdoutoradoreponame:Repositório Institucional da UFPEinstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEORIGINALTESE Kellyton dos Santos Brito.pdfTESE Kellyton dos Santos Brito.pdfapplication/pdf3360410https://repositorio.ufpe.br/bitstream/123456789/40462/1/TESE%20Kellyton%20dos%20Santos%20Brito.pdfb9ec91b24a952e79ba1bde3d17d061ceMD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8811https://repositorio.ufpe.br/bitstream/123456789/40462/2/license_rdfe39d27027a6cc9cb039ad269a5db8e34MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-82310https://repositorio.ufpe.br/bitstream/123456789/40462/3/license.txtbd573a5ca8288eb7272482765f819534MD53TEXTTESE Kellyton dos Santos Brito.pdf.txtTESE Kellyton dos Santos Brito.pdf.txtExtracted texttext/plain348387https://repositorio.ufpe.br/bitstream/123456789/40462/4/TESE%20Kellyton%20dos%20Santos%20Brito.pdf.txtdb915168db78a9d29268b9fd35ca9c39MD54THUMBNAILTESE Kellyton dos Santos Brito.pdf.jpgTESE Kellyton dos Santos Brito.pdf.jpgGenerated Thumbnailimage/jpeg1240https://repositorio.ufpe.br/bitstream/123456789/40462/5/TESE%20Kellyton%20dos%20Santos%20Brito.pdf.jpg145f228aa72de466d19c7c8437a4070cMD55123456789/404622021-07-09 02:20:44.785oai:repositorio.ufpe.br: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ório InstitucionalPUBhttps://repositorio.ufpe.br/oai/requestattena@ufpe.bropendoar:22212021-07-09T05:20:44Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE)false |
dc.title.pt_BR.fl_str_mv |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
title |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
spellingShingle |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls BRITO, Kellyton dos Santos Inteligência Computacional Redes sociais Eleições Aprendizado de máquinas |
title_short |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
title_full |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
title_fullStr |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
title_full_unstemmed |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
title_sort |
Machine learning for nowcasting elections in Latin America based on social media engagement and polls |
author |
BRITO, Kellyton dos Santos |
author_facet |
BRITO, Kellyton dos Santos |
author_role |
author |
dc.contributor.authorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/8750956715158540 |
dc.contributor.advisorLattes.pt_BR.fl_str_mv |
http://lattes.cnpq.br/3524590211304012 |
dc.contributor.author.fl_str_mv |
BRITO, Kellyton dos Santos |
dc.contributor.advisor1.fl_str_mv |
ADEODATO, Paulo Jorge Leitão |
contributor_str_mv |
ADEODATO, Paulo Jorge Leitão |
dc.subject.por.fl_str_mv |
Inteligência Computacional Redes sociais Eleições Aprendizado de máquinas |
topic |
Inteligência Computacional Redes sociais Eleições Aprendizado de máquinas |
description |
Contemporary social media (SM) represents a new communication paradigm and has impacted politics and electoral campaigns. The mobilization of the Arab Spring social movements was attributed to SM platforms, as well as successful electoral campaigns such as those of Obama and Trump in the U.S. (2008, 2012, and 2016), the Brexit campaign in 2016, and the Bolsonaro campaign for the Brazilian presidency in 2018. Within this new scenario, the advantages of collecting SM data over traditional polling methods include the huge volume of available data, the high speed, and low costs. Hence, researchers are endeavoring to discover how to use SM for nowcasting election results. However, despite the alleged success, the most-common approach, based on counting the volume of mentions on Twitter and conducting a sentiment analysis, has been frequently criticized and challenged. On the other hand, recent approaches based on other SM platforms and on the advances of machine learning (ML) may be promising alternatives. In this context, this thesis aims to advance the state-of-the-art on predicting elections based on SM data. It proposes a new set of SM performance metrics to be input features for the ML techniques by changing the focus onto the number of people paying attention to the candidates. The defined metrics may be used not only with the most commonly-used current SM platforms (i.e., Facebook, Instagram, and Twitter) but even with future platforms which have not yet gained popularity. In addition, this thesis defines SoMEN, the Social Media framework for Election Nowcasting, a framework composed of a process and model for nowcasting election results based on the SM performance features and using ML approaches. It proposes well-defined steps, ranging from election understanding to prediction evaluation, and an ML model for predicting the final election results based on an ensemble of artificial neural networks (ANN) trained with SM metrics as features and offline polls as labeled data. It also defines SoMEN-DC, an execution strategy for SoMEN that enables continuous prediction during the campaign (DC). The proposed metrics and framework were applied on the most recent main presidential elections in Latin America: Argentina (2019), Brazil (2018), Colombia (2018), and Mexico (2018). More than 65,000 posts were collected from the SM profiles on Facebook, Twitter, and Instagram of the candidates, as well as data from 195 presidential polls. Results demonstrated that the defined metrics presented a high correlation with the final share of votes in all the studied countries. Moreover, it was also possible to achieve a high level of accuracy in predicting the final vote share of the candidates, with competitive or better results than traditional polls. Lastly, despite the difficulty in measuring the quality of predictions during the campaign, results are promising and also competitive to polls. The strategies put forward in this thesis have attempted to handle several among the current challenges in this research area and indicate a new manner on how to face the problems. Furthermore, they may be directly used for nowcasting future elections in similar scenarios. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-07-08T19:46:43Z |
dc.date.available.fl_str_mv |
2021-07-08T19:46:43Z |
dc.date.issued.fl_str_mv |
2021-03-18 |
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.citation.fl_str_mv |
BRITO, Kellyton dos Santos. Machine learning for nowcasting elections in Latin America based on social media engagement and polls. 2021. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2021. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufpe.br/handle/123456789/40462 |
identifier_str_mv |
BRITO, Kellyton dos Santos. Machine learning for nowcasting elections in Latin America based on social media engagement and polls. 2021. Tese (Doutorado em Ciência da Computação) – Universidade Federal de Pernambuco, Recife, 2021. |
url |
https://repositorio.ufpe.br/handle/123456789/40462 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivs 3.0 Brazil http://creativecommons.org/licenses/by-nc-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.publisher.program.fl_str_mv |
Programa de Pos Graduacao em Ciencia da Computacao |
dc.publisher.initials.fl_str_mv |
UFPE |
dc.publisher.country.fl_str_mv |
Brasil |
publisher.none.fl_str_mv |
Universidade Federal de Pernambuco |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFPE instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Repositório Institucional da UFPE |
collection |
Repositório Institucional da UFPE |
bitstream.url.fl_str_mv |
https://repositorio.ufpe.br/bitstream/123456789/40462/1/TESE%20Kellyton%20dos%20Santos%20Brito.pdf https://repositorio.ufpe.br/bitstream/123456789/40462/2/license_rdf https://repositorio.ufpe.br/bitstream/123456789/40462/3/license.txt https://repositorio.ufpe.br/bitstream/123456789/40462/4/TESE%20Kellyton%20dos%20Santos%20Brito.pdf.txt https://repositorio.ufpe.br/bitstream/123456789/40462/5/TESE%20Kellyton%20dos%20Santos%20Brito.pdf.jpg |
bitstream.checksum.fl_str_mv |
b9ec91b24a952e79ba1bde3d17d061ce e39d27027a6cc9cb039ad269a5db8e34 bd573a5ca8288eb7272482765f819534 db915168db78a9d29268b9fd35ca9c39 145f228aa72de466d19c7c8437a4070c |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFPE - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
attena@ufpe.br |
_version_ |
1802310900165640192 |