Misinformation, radicalization and hate through the lens of users
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFMG |
Texto Completo: | http://hdl.handle.net/1843/46708 |
Resumo: | The popularization of Online Social Networks has changed the dynamics of content creation and consumption. Barriers to disseminate texts, images and videos became significantly lower than in earlier times, empowering users to create, with little resources, content with far-reaching impact. In this setting, society has witnessed an amplification in phenomena such as misinformation and hate speech. Recent research attempts to address these issues by studying hateful or fake content. Yet, robustly addressing these phenomena in this fashion is often not feasible. Consider for example the task of detecting hate speech. There can be two exact texts that, in different contexts (e.g. a rap lyric and a politician's speech), may be considered to be hateful or not. Moreover, there may even be that, given a text within a context, two individuals disagree on whether the content is hateful or not. This dissertation attempts to address these issues by taking another perspective: that of the user. Through the lens of users, it is possible to approach possibly fake or hateful content with surrounding context: political orientation, activity patterns, connections, etc. Furthermore, we can study more complex phenomenon, such as user radicalization, where one must study the trajectories of individuals -- or, more realistically, their online traces. In three case studies on social networks, we: (i) provide insight on how the perception of what is misinformation is altered by political opinion; (ii) propose a methodology to study hate speech on a user-level, showing that the network structure of users can improve the detection of the phenomenon; (iii) characterize user radicalization in far-right channels on YouTube through time, showing a growing migration towards the consumption of extreme content in the platform. Each case study contributes to their more specific subject: misinformation, hate speech and user radicalization. Yet, altogether, they advance a central argument: that studying users rather than the content itself is more productive to better understand (and eventually mitigate) ill-defined social phenomena such as hate speech and fake news. |
id |
UFMG_5802b4193dbc3debd2b830375172a131 |
---|---|
oai_identifier_str |
oai:repositorio.ufmg.br:1843/46708 |
network_acronym_str |
UFMG |
network_name_str |
Repositório Institucional da UFMG |
repository_id_str |
|
spelling |
Wagner Meira Juniorhttp://lattes.cnpq.br/9092587237114334Virgilio Augusto Fernandes Almeidahttp://lattes.cnpq.br/9417286617377998Vírgilio Augusto Fernandes de AlmeidaLuis da Cunha LambPedro Olmo Stancioli Vaz de MeloJussara Marques de Almeida Gonçalveshttp://lattes.cnpq.br/1069141361567921Manoel Horta Ribeiro2022-10-27T18:40:28Z2022-10-27T18:40:28Z2019-08-13http://hdl.handle.net/1843/46708The popularization of Online Social Networks has changed the dynamics of content creation and consumption. Barriers to disseminate texts, images and videos became significantly lower than in earlier times, empowering users to create, with little resources, content with far-reaching impact. In this setting, society has witnessed an amplification in phenomena such as misinformation and hate speech. Recent research attempts to address these issues by studying hateful or fake content. Yet, robustly addressing these phenomena in this fashion is often not feasible. Consider for example the task of detecting hate speech. There can be two exact texts that, in different contexts (e.g. a rap lyric and a politician's speech), may be considered to be hateful or not. Moreover, there may even be that, given a text within a context, two individuals disagree on whether the content is hateful or not. This dissertation attempts to address these issues by taking another perspective: that of the user. Through the lens of users, it is possible to approach possibly fake or hateful content with surrounding context: political orientation, activity patterns, connections, etc. Furthermore, we can study more complex phenomenon, such as user radicalization, where one must study the trajectories of individuals -- or, more realistically, their online traces. In three case studies on social networks, we: (i) provide insight on how the perception of what is misinformation is altered by political opinion; (ii) propose a methodology to study hate speech on a user-level, showing that the network structure of users can improve the detection of the phenomenon; (iii) characterize user radicalization in far-right channels on YouTube through time, showing a growing migration towards the consumption of extreme content in the platform. Each case study contributes to their more specific subject: misinformation, hate speech and user radicalization. Yet, altogether, they advance a central argument: that studying users rather than the content itself is more productive to better understand (and eventually mitigate) ill-defined social phenomena such as hate speech and fake news.A popularização das redes sociais mudou a dinâmica de criação e consumo de conteúdo. Barreiras para disseminar textos, imagens e vídeos tornaram-se significativamente menores do que em épocas anteriores, capacitando os usuários a criar, com poucos recursos, conteúdo de impacto e de longo alcance. Neste cenário, a sociedade testemunhou a amplificação de fenômenos como a desinformação e discurso de ódio. Pesquisas recentes tentam resolver esses problemas estudando conteúdo odioso ou falso. No entanto, abordar com robustez esses fenômenos desta maneira muitas vezes não é viável. Considere, por exemplo, a tarefa de detectar o discurso de ódio. Pode haver dois textos iguais que, em diferentes contextos (por exemplo, uma letra de rap e o discurso de um político) podem ser considerados odiosos ou não. Além disso, pode ser que, dado um texto dentro de um contexto, dois indivíduos discordem sobre se o conteúdo é odioso ou não. Esta dissertação tenta abordar estes problemas tomando outra perspectiva: a do usuário. Através da perspectiva do usuário, é possível abordar conteúdos possivelmente falsos ou odiosos com o contexto circundante: orientação política, padrões de atividade, conexões, etc. Além disso, somos capazes de estudar fenômenos mais complexos, como a radicalização de usuários, onde devemos estudar as trajetórias dos indivíduos ---ou, mais realisticamente, seus traços on-line. Em três estudos de caso em redes sociais, nós: (i)~fornecemos insights sobre como a percepção do que é desinformação é alterada pela opinião política; (ii)~propomos uma metodologia para estudar o discurso de ódio no nível do usuário, mostrando que a estrutura de rede dos usuários pode melhorar muito a detecção do fenômeno; e (iii)~caracterizamos a radicalização de usuários em canais no YouTube ao longo do tempo, mostrando uma migração crescente para canais mais extremos. Cada estudo de caso contribui para seu assunto mais específico: desinformação, discurso de ódio e radicalização. Em conjunto, eles suportam um argumento central: o de que devemos estudar fenômenos mal definidos como desinformação e o discurso de ódio sob a perspectiva dos usuários.engUniversidade Federal de Minas GeraisPrograma de Pós-Graduação em Ciência da ComputaçãoUFMGBrasilICX - DEPARTAMENTO DE CIÊNCIA DA COMPUTAÇÃOhttp://creativecommons.org/licenses/by/3.0/pt/info:eu-repo/semantics/openAccessComputação - TesesRedes sociais on-line - TesesDesinformação - TesesFake news - TesesSocial networksHate speechMisinformationRadicalizationMisinformation, radicalization and hate through the lens of usersDesinformação, radicalização e ódio na perspectiva dos usuáriosinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisreponame:Repositório Institucional da UFMGinstname:Universidade Federal de Minas Gerais (UFMG)instacron:UFMGORIGINALMaster_Thesis.pdfMaster_Thesis.pdfapplication/pdf5236058https://repositorio.ufmg.br/bitstream/1843/46708/5/Master_Thesis.pdf170565ab17358c473aea91b132093b5eMD55CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8914https://repositorio.ufmg.br/bitstream/1843/46708/6/license_rdff9944a358a0c32770bd9bed185bb5395MD56LICENSElicense.txtlicense.txttext/plain; charset=utf-82118https://repositorio.ufmg.br/bitstream/1843/46708/7/license.txtcda590c95a0b51b4d15f60c9642ca272MD571843/467082022-10-27 15:40:28.58oai:repositorio.ufmg.br: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ório de PublicaçõesPUBhttps://repositorio.ufmg.br/oaiopendoar:2022-10-27T18:40:28Repositório Institucional da UFMG - Universidade Federal de Minas Gerais (UFMG)false |
dc.title.pt_BR.fl_str_mv |
Misinformation, radicalization and hate through the lens of users |
dc.title.alternative.pt_BR.fl_str_mv |
Desinformação, radicalização e ódio na perspectiva dos usuários |
title |
Misinformation, radicalization and hate through the lens of users |
spellingShingle |
Misinformation, radicalization and hate through the lens of users Manoel Horta Ribeiro Social networks Hate speech Misinformation Radicalization Computação - Teses Redes sociais on-line - Teses Desinformação - Teses Fake news - Teses |
title_short |
Misinformation, radicalization and hate through the lens of users |
title_full |
Misinformation, radicalization and hate through the lens of users |
title_fullStr |
Misinformation, radicalization and hate through the lens of users |
title_full_unstemmed |
Misinformation, radicalization and hate through the lens of users |
title_sort |
Misinformation, radicalization and hate through the lens of users |
author |
Manoel Horta Ribeiro |
author_facet |
Manoel Horta Ribeiro |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Wagner Meira Junior |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/9092587237114334 |
dc.contributor.advisor2.fl_str_mv |
Virgilio Augusto Fernandes Almeida |
dc.contributor.advisor2Lattes.fl_str_mv |
http://lattes.cnpq.br/9417286617377998 |
dc.contributor.advisor-co1.fl_str_mv |
Vírgilio Augusto Fernandes de Almeida |
dc.contributor.referee1.fl_str_mv |
Luis da Cunha Lamb |
dc.contributor.referee2.fl_str_mv |
Pedro Olmo Stancioli Vaz de Melo |
dc.contributor.referee3.fl_str_mv |
Jussara Marques de Almeida Gonçalves |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/1069141361567921 |
dc.contributor.author.fl_str_mv |
Manoel Horta Ribeiro |
contributor_str_mv |
Wagner Meira Junior Virgilio Augusto Fernandes Almeida Vírgilio Augusto Fernandes de Almeida Luis da Cunha Lamb Pedro Olmo Stancioli Vaz de Melo Jussara Marques de Almeida Gonçalves |
dc.subject.por.fl_str_mv |
Social networks Hate speech Misinformation Radicalization |
topic |
Social networks Hate speech Misinformation Radicalization Computação - Teses Redes sociais on-line - Teses Desinformação - Teses Fake news - Teses |
dc.subject.other.pt_BR.fl_str_mv |
Computação - Teses Redes sociais on-line - Teses Desinformação - Teses Fake news - Teses |
description |
The popularization of Online Social Networks has changed the dynamics of content creation and consumption. Barriers to disseminate texts, images and videos became significantly lower than in earlier times, empowering users to create, with little resources, content with far-reaching impact. In this setting, society has witnessed an amplification in phenomena such as misinformation and hate speech. Recent research attempts to address these issues by studying hateful or fake content. Yet, robustly addressing these phenomena in this fashion is often not feasible. Consider for example the task of detecting hate speech. There can be two exact texts that, in different contexts (e.g. a rap lyric and a politician's speech), may be considered to be hateful or not. Moreover, there may even be that, given a text within a context, two individuals disagree on whether the content is hateful or not. This dissertation attempts to address these issues by taking another perspective: that of the user. Through the lens of users, it is possible to approach possibly fake or hateful content with surrounding context: political orientation, activity patterns, connections, etc. Furthermore, we can study more complex phenomenon, such as user radicalization, where one must study the trajectories of individuals -- or, more realistically, their online traces. In three case studies on social networks, we: (i) provide insight on how the perception of what is misinformation is altered by political opinion; (ii) propose a methodology to study hate speech on a user-level, showing that the network structure of users can improve the detection of the phenomenon; (iii) characterize user radicalization in far-right channels on YouTube through time, showing a growing migration towards the consumption of extreme content in the platform. Each case study contributes to their more specific subject: misinformation, hate speech and user radicalization. Yet, altogether, they advance a central argument: that studying users rather than the content itself is more productive to better understand (and eventually mitigate) ill-defined social phenomena such as hate speech and fake news. |
publishDate |
2019 |
dc.date.issued.fl_str_mv |
2019-08-13 |
dc.date.accessioned.fl_str_mv |
2022-10-27T18:40:28Z |
dc.date.available.fl_str_mv |
2022-10-27T18:40:28Z |
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/1843/46708 |
url |
http://hdl.handle.net/1843/46708 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by/3.0/pt/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by/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/1843/46708/5/Master_Thesis.pdf https://repositorio.ufmg.br/bitstream/1843/46708/6/license_rdf https://repositorio.ufmg.br/bitstream/1843/46708/7/license.txt |
bitstream.checksum.fl_str_mv |
170565ab17358c473aea91b132093b5e f9944a358a0c32770bd9bed185bb5395 cda590c95a0b51b4d15f60c9642ca272 |
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_ |
1803589539795566592 |