Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Biblioteca Digital de Teses e Dissertações da UFPB |
Texto Completo: | https://repositorio.ufpb.br/jspui/handle/123456789/18208 |
Resumo: | The aim of this paper was to identify, through the messages that are posted on Twitter, how the information that is disseminated online is associated with the movements that occur in the Brazilian market, specifically with regard to returns and traded volume. The collection of data related to Twitter took place through the Tweepy library. Financial data were obtained using the Thomson Reuters database. For the development of the sentiment index, a netnographic method was used, in which there was a participant observation in the social network Twitter in order to know the terms that are used to refer to the Brazilian market and the stocks that compose it. The sentiment was attributed through machine learning, by the Google Cloud Natural Language API, which has a sentiment analysis tool. To reach the general objective of the research, seven quantile regression models were estimated in five quantiles, since the data obtained were heterogeneous and did not demonstrate normality, since this type of regression is robust to such problems, so it was possible to have an understanding of the subject and interpretation of data. The analysis and interpretation of the data made it possible to perceive that, in general, an optimistic sentiment in contemporary time will be associated with a greater contemporary return, however this relationship is inverted over the days, so that, an optimistic sentiment in the current period will be associated with a subsequent lower return. It was also found that there is a significant association between the volume of messages that are posted daily on Twitter and traded volume of the Brazilian stock market. In addition, it was seen that the greater the number of messages that have a negative feeling, the greater the traded volume. Thus, it is believed that the results are useful to show that there is a relationship between the information that is released on the social network Twitter and the movements of the Brazilian stock market, bringing contributions to the literature, by expanding the understanding of how emerging markets are associated with activities that occur in the online environment. The study also has practical contributions, since activities that occur online on Twitter can be used as variables in investment strategies, since these are associated with market movements |
id |
UFPB_45446179fb8b43d44160c216fd7075a4 |
---|---|
oai_identifier_str |
oai:repositorio.ufpb.br:123456789/18208 |
network_acronym_str |
UFPB |
network_name_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository_id_str |
|
spelling |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiroAnálise de sentimentoTwitterMercado acionárioSentiment analysisStock marketCNPQ::CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO::CIENCIAS CONTABEISThe aim of this paper was to identify, through the messages that are posted on Twitter, how the information that is disseminated online is associated with the movements that occur in the Brazilian market, specifically with regard to returns and traded volume. The collection of data related to Twitter took place through the Tweepy library. Financial data were obtained using the Thomson Reuters database. For the development of the sentiment index, a netnographic method was used, in which there was a participant observation in the social network Twitter in order to know the terms that are used to refer to the Brazilian market and the stocks that compose it. The sentiment was attributed through machine learning, by the Google Cloud Natural Language API, which has a sentiment analysis tool. To reach the general objective of the research, seven quantile regression models were estimated in five quantiles, since the data obtained were heterogeneous and did not demonstrate normality, since this type of regression is robust to such problems, so it was possible to have an understanding of the subject and interpretation of data. The analysis and interpretation of the data made it possible to perceive that, in general, an optimistic sentiment in contemporary time will be associated with a greater contemporary return, however this relationship is inverted over the days, so that, an optimistic sentiment in the current period will be associated with a subsequent lower return. It was also found that there is a significant association between the volume of messages that are posted daily on Twitter and traded volume of the Brazilian stock market. In addition, it was seen that the greater the number of messages that have a negative feeling, the greater the traded volume. Thus, it is believed that the results are useful to show that there is a relationship between the information that is released on the social network Twitter and the movements of the Brazilian stock market, bringing contributions to the literature, by expanding the understanding of how emerging markets are associated with activities that occur in the online environment. The study also has practical contributions, since activities that occur online on Twitter can be used as variables in investment strategies, since these are associated with market movementsNenhumaO objetivo desse estudo foi identificar, por meio das mensagens que são postadas no Twitter, como as informações que são divulgados de forma on-line estão associadas aos movimentos que ocorrem no mercado brasileiro, especificamente no que tange aos retornos e ao volume de negócios. A coleta dos dados relacionados ao Twitter se deu por meio da biblioteca Tweepy. Já os dados financeiros foram obtidos mediante a base de dados Thomson Reuters. Para o desenvolvimento do índice de sentimento foi empregado um método netnográfico, no qual houve uma observação participante na rede social Twitter de modo a conhecer os termos que são utilizados a se referir ao mercado brasileiro e as ações que o compõem. A atribuição do sentimento se deu por meio de machine learning, por intermédio do Google Cloud Natural Language API, o qual possui uma ferramenta de análise de sentimentos. Para atender ao objetivo geral da pesquisa foram estimados sete modelos de regressão quantílica em cinco quantis, uma vez que os dados obtidos eram heterogêneos e não demonstravam normalidade, visto que esse tipo de regressão apresenta robustez para tais problemas, assim foi possível ter uma compreensão do assunto e interpretação dos dados. A análise e intepretação dos dados possibilitou perceber que, em geral, um sentimento otimista no tempo contemporâneo estará associado a um maior retorno contemporâneo, todavia essa relação se inverte com o passar dos dias, de modo que, um sentimento otimista no período atual estará associado a um menor retorno subsequente. Constatou-se ainda que existe associação entre o volume de mensagens que são postadas diariamente no Twitter e o volume de negócios do mercado acionário brasileiro. Ademais, viu-se que quão maior for o número de mensagens que são dotadas de um sentimento negativo, maior também será o volume negociado. Assim, os resultados são úteis para mostrar que existe relação entre as informações que são divulgadas na rede social Twitter e os movimentos do mercado acionário brasileiro, trazendo contribuições para a literatura, ao expandir o entendimento de como mercados emergentes estão associados às atividades que ocorrem no ambiente on-line. O estudo também traz contribuições práticas, uma vez que as atividades que ocorrem on-line no Twitter podem ser utilizadas como variáveis em estratégias de investimento, visto que essas estão associadas aos movimentos do mercadoUniversidade Federal da ParaíbaBrasilFinanças e ContabilidadePrograma de Pós-Graduação em Ciências ContábeisUFPBMartins, Orleans Silvahttp://lattes.cnpq.br/5012236039984008Souza, Dyliane Mourí Silva de2020-10-19T19:31:41Z2020-04-132020-10-19T19:31:41Z2020-02-21info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesishttps://repositorio.ufpb.br/jspui/handle/123456789/18208porhttp://creativecommons.org/licenses/by-nd/3.0/br/info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da UFPBinstname:Universidade Federal da Paraíba (UFPB)instacron:UFPB2021-09-17T23:03:32Zoai:repositorio.ufpb.br:123456789/18208Biblioteca Digital de Teses e Dissertaçõeshttps://repositorio.ufpb.br/PUBhttp://tede.biblioteca.ufpb.br:8080/oai/requestdiretoria@ufpb.br|| diretoria@ufpb.bropendoar:2021-09-17T23:03:32Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB)false |
dc.title.none.fl_str_mv |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
title |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
spellingShingle |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro Souza, Dyliane Mourí Silva de Análise de sentimento Mercado acionário Sentiment analysis Stock market CNPQ::CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO::CIENCIAS CONTABEIS |
title_short |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
title_full |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
title_fullStr |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
title_full_unstemmed |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
title_sort |
Efeito do sentimento do investidor manifesto via Twitter sobre os retornos e o volume negociado no mercado acionário brasileiro |
author |
Souza, Dyliane Mourí Silva de |
author_facet |
Souza, Dyliane Mourí Silva de |
author_role |
author |
dc.contributor.none.fl_str_mv |
Martins, Orleans Silva http://lattes.cnpq.br/5012236039984008 |
dc.contributor.author.fl_str_mv |
Souza, Dyliane Mourí Silva de |
dc.subject.por.fl_str_mv |
Análise de sentimento Mercado acionário Sentiment analysis Stock market CNPQ::CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO::CIENCIAS CONTABEIS |
topic |
Análise de sentimento Mercado acionário Sentiment analysis Stock market CNPQ::CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO::CIENCIAS CONTABEIS |
description |
The aim of this paper was to identify, through the messages that are posted on Twitter, how the information that is disseminated online is associated with the movements that occur in the Brazilian market, specifically with regard to returns and traded volume. The collection of data related to Twitter took place through the Tweepy library. Financial data were obtained using the Thomson Reuters database. For the development of the sentiment index, a netnographic method was used, in which there was a participant observation in the social network Twitter in order to know the terms that are used to refer to the Brazilian market and the stocks that compose it. The sentiment was attributed through machine learning, by the Google Cloud Natural Language API, which has a sentiment analysis tool. To reach the general objective of the research, seven quantile regression models were estimated in five quantiles, since the data obtained were heterogeneous and did not demonstrate normality, since this type of regression is robust to such problems, so it was possible to have an understanding of the subject and interpretation of data. The analysis and interpretation of the data made it possible to perceive that, in general, an optimistic sentiment in contemporary time will be associated with a greater contemporary return, however this relationship is inverted over the days, so that, an optimistic sentiment in the current period will be associated with a subsequent lower return. It was also found that there is a significant association between the volume of messages that are posted daily on Twitter and traded volume of the Brazilian stock market. In addition, it was seen that the greater the number of messages that have a negative feeling, the greater the traded volume. Thus, it is believed that the results are useful to show that there is a relationship between the information that is released on the social network Twitter and the movements of the Brazilian stock market, bringing contributions to the literature, by expanding the understanding of how emerging markets are associated with activities that occur in the online environment. The study also has practical contributions, since activities that occur online on Twitter can be used as variables in investment strategies, since these are associated with market movements |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-10-19T19:31:41Z 2020-04-13 2020-10-19T19:31:41Z 2020-02-21 |
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 |
https://repositorio.ufpb.br/jspui/handle/123456789/18208 |
url |
https://repositorio.ufpb.br/jspui/handle/123456789/18208 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nd/3.0/br/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nd/3.0/br/ |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Finanças e Contabilidade Programa de Pós-Graduação em Ciências Contábeis UFPB |
publisher.none.fl_str_mv |
Universidade Federal da Paraíba Brasil Finanças e Contabilidade Programa de Pós-Graduação em Ciências Contábeis UFPB |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da UFPB instname:Universidade Federal da Paraíba (UFPB) instacron:UFPB |
instname_str |
Universidade Federal da Paraíba (UFPB) |
instacron_str |
UFPB |
institution |
UFPB |
reponame_str |
Biblioteca Digital de Teses e Dissertações da UFPB |
collection |
Biblioteca Digital de Teses e Dissertações da UFPB |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da UFPB - Universidade Federal da Paraíba (UFPB) |
repository.mail.fl_str_mv |
diretoria@ufpb.br|| diretoria@ufpb.br |
_version_ |
1798963967852281856 |