Aplicação de programação genética na análise de sentimentos
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFG |
dARK ID: | ark:/38995/001300000b84q |
Texto Completo: | http://repositorio.bc.ufg.br/tede/handle/tede/9211 |
Resumo: | The Web is commonly used as a platform for debates, opinions, evaluations, etc. These data allowed the area of Sentiment Analysis (SA) to develop to extract information and knowledge that can be used in different applications. Among the challenges of SA we can highlight the creation of classifiers with good efficacy. Typically, the classification models are generated using specific heuristics, manually defined and not adaptable to different contexts. Thus, this work proposes the automated generation of hybrid SA classifiers - with Machine Learning (ML) techniques and lexical dictionaries - using Genetic Programming (GP). It is expected to reduce the cost of generating the classifiers and increase the predictive power for each domain analyzed. The goal is that these classifiers will be competitive with the classical ML algorithms used in SA, generalizable, adaptable to the context and able to determine the relevance of each lexical to the applied domain. In addition, the aim is allow to aggregate other ML techniques to create even more effective hybrid solutions. In order to validate the proposal, SemEval 2014 benchmark was used. The results show that the approach with GP is promising since the generated models are competitive, and sometimes better, with other researches. The ensemble proved to be effective in increasing the predictive power of the system, obtaining better results than the use of the techniques individually. Finally, we highlight the ability of models customization according to the context approached and the possibility of knowledge transfer of the users through the functions used by GP. |
id |
UFG-2_7c7ddcc7dc6dc9ab23bf8f8b45cbe5a8 |
---|---|
oai_identifier_str |
oai:repositorio.bc.ufg.br:tede/9211 |
network_acronym_str |
UFG-2 |
network_name_str |
Repositório Institucional da UFG |
repository_id_str |
|
spelling |
Silva, Nádia Félix Felipe dahttp://lattes.cnpq.br/7864834001694765Camilo Junior, Celso Gonçalveshttp://lattes.cnpq.br/6776569904919279Silva, Nádia Félix Felipe daCamilo Junior, Celso GonçalvesRosa, Thierson CoutoCovões, Thiago FerreiraFernandes, Deborah Silva Alveshttp://lattes.cnpq.br/5718967602727513Bordin Junior, Airton2019-01-09T11:18:52Z2018-12-14BORDIN JUNIOR, A. Aplicação de programação genética na análise de sentimentos. 2018. 142 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2018.http://repositorio.bc.ufg.br/tede/handle/tede/9211ark:/38995/001300000b84qThe Web is commonly used as a platform for debates, opinions, evaluations, etc. These data allowed the area of Sentiment Analysis (SA) to develop to extract information and knowledge that can be used in different applications. Among the challenges of SA we can highlight the creation of classifiers with good efficacy. Typically, the classification models are generated using specific heuristics, manually defined and not adaptable to different contexts. Thus, this work proposes the automated generation of hybrid SA classifiers - with Machine Learning (ML) techniques and lexical dictionaries - using Genetic Programming (GP). It is expected to reduce the cost of generating the classifiers and increase the predictive power for each domain analyzed. The goal is that these classifiers will be competitive with the classical ML algorithms used in SA, generalizable, adaptable to the context and able to determine the relevance of each lexical to the applied domain. In addition, the aim is allow to aggregate other ML techniques to create even more effective hybrid solutions. In order to validate the proposal, SemEval 2014 benchmark was used. The results show that the approach with GP is promising since the generated models are competitive, and sometimes better, with other researches. The ensemble proved to be effective in increasing the predictive power of the system, obtaining better results than the use of the techniques individually. Finally, we highlight the ability of models customization according to the context approached and the possibility of knowledge transfer of the users through the functions used by GP.A Web é comumente utilizada como plataforma para debates, opiniões, avaliações, etc. Esses dados permitiram que a área de Análise de Sentimentos (AS) se desenvolvesse para extrair informações e conhecimentos que possam ser utilizados em diferentes aplicações. Entre os desafios da AS, destacam-se a criação de classificadores com boa eficácia. Normalmente, os modelos de classificação gerados são heurísticas específicas, manualmente definidas e pouco adaptáveis a diferentes contextos. Assim, o presente trabalho propõe a geração automatizada de classificadores de sentimentos híbridos – utilizando técnicas de Aprendizado de Máquina (AM) e dicionários léxicos – com o uso da Programação Genética (PG). Com isso, espera-se reduzir o custo de geração dos classificadores e aumentar o poder de predição para cada domínio analisado. A intenção é que esses classificadores sejam competitivos com os algoritmos clássicos empregados na área de AS, generalizáveis, adaptáveis ao contexto e capazes de determinar a relevância de cada um dos dicionários léxicos ao domínio aplicado. Além disso, a ideia é que seja possível a agregação de outras técnicas de AM para a geração de soluções híbridas ainda mais eficazes. Para validar a proposta, foi utilizado o benchmark SemEval 2014 e os resultados mostram que a abordagem de geração automatizada com a PG é promissora, pois os modelos gerados são competitivos e, algumas vezes, superiores aos de outros trabalhos da literatura. A combinação dos classificadores em um comitê mostrou-se eficaz ao aumento do poder de predição do sistema, obtendo resultados superiores à utilização das técnicas individualmente. Por fim, destaca-se a capacidade de customização dos modelos de acordo com o contexto abordado e a possibilidade de transferência de conhecimento dos usuários por meio das funções utilizadas pela PG.Submitted by Ana Caroline Costa (ana_caroline212@hotmail.com) on 2019-01-08T17:57:49Z No. of bitstreams: 2 Dissertação - Airton Bordin Junior - 2018.pdf: 1915483 bytes, checksum: ce3cc567ea43be5719b609ec785f5200 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2019-01-09T11:18:52Z (GMT) No. of bitstreams: 2 Dissertação - Airton Bordin Junior - 2018.pdf: 1915483 bytes, checksum: ce3cc567ea43be5719b609ec785f5200 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)Made available in DSpace on 2019-01-09T11:18:52Z (GMT). No. of bitstreams: 2 Dissertação - Airton Bordin Junior - 2018.pdf: 1915483 bytes, checksum: ce3cc567ea43be5719b609ec785f5200 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2018-12-14Conselho Nacional de Pesquisa e Desenvolvimento Científico e Tecnológico - CNPqapplication/pdfporUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RG)http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAnálise de sentimentosMineração de opiniõesProgramação genéticaClassificadoresSentiment analysisOpinion miningGenetic programmingClassifiersCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOAplicação de programação genética na análise de sentimentosApplying genetic programming to sentiment analysisinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis-3303550325223384799600600600600-77122667346336447683671711205811204509-2555911436985713659reponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGLICENSElicense.txtlicense.txttext/plain; charset=utf-82165http://repositorio.bc.ufg.br/tede/bitstreams/f11ef502-b860-434d-8b3a-47ac3c23de30/downloadbd3efa91386c1718a7f26a329fdcb468MD51CC-LICENSElicense_urllicense_urltext/plain; charset=utf-849http://repositorio.bc.ufg.br/tede/bitstreams/77dc6309-5b43-4736-9c6c-5a20eedc8271/download4afdbb8c545fd630ea7db775da747b2fMD52license_textlicense_texttext/html; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/92bd49b7-1ec7-4a54-967d-2189cee9bafb/downloadd41d8cd98f00b204e9800998ecf8427eMD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-80http://repositorio.bc.ufg.br/tede/bitstreams/d544cef1-cb91-42c5-839a-9c473ecdf2bc/downloadd41d8cd98f00b204e9800998ecf8427eMD54ORIGINALDissertação - Airton Bordin Junior - 2018.pdfDissertação - Airton Bordin Junior - 2018.pdfapplication/pdf1915483http://repositorio.bc.ufg.br/tede/bitstreams/445fab3c-9d3a-42ff-9547-443b597f4dd7/downloadce3cc567ea43be5719b609ec785f5200MD55tede/92112019-01-09 09:18:52.267http://creativecommons.org/licenses/by-nc-nd/4.0/Acesso Abertoopen.accessoai:repositorio.bc.ufg.br:tede/9211http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttp://repositorio.bc.ufg.br/oai/requesttasesdissertacoes.bc@ufg.bropendoar:2019-01-09T11:18:52Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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 |
dc.title.eng.fl_str_mv |
Aplicação de programação genética na análise de sentimentos |
dc.title.alternative.eng.fl_str_mv |
Applying genetic programming to sentiment analysis |
title |
Aplicação de programação genética na análise de sentimentos |
spellingShingle |
Aplicação de programação genética na análise de sentimentos Bordin Junior, Airton Análise de sentimentos Mineração de opiniões Programação genética Classificadores Sentiment analysis Opinion mining Genetic programming Classifiers CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Aplicação de programação genética na análise de sentimentos |
title_full |
Aplicação de programação genética na análise de sentimentos |
title_fullStr |
Aplicação de programação genética na análise de sentimentos |
title_full_unstemmed |
Aplicação de programação genética na análise de sentimentos |
title_sort |
Aplicação de programação genética na análise de sentimentos |
author |
Bordin Junior, Airton |
author_facet |
Bordin Junior, Airton |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Silva, Nádia Félix Felipe da |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/7864834001694765 |
dc.contributor.advisor-co1.fl_str_mv |
Camilo Junior, Celso Gonçalves |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://lattes.cnpq.br/6776569904919279 |
dc.contributor.referee1.fl_str_mv |
Silva, Nádia Félix Felipe da |
dc.contributor.referee2.fl_str_mv |
Camilo Junior, Celso Gonçalves |
dc.contributor.referee3.fl_str_mv |
Rosa, Thierson Couto |
dc.contributor.referee4.fl_str_mv |
Covões, Thiago Ferreira |
dc.contributor.referee5.fl_str_mv |
Fernandes, Deborah Silva Alves |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/5718967602727513 |
dc.contributor.author.fl_str_mv |
Bordin Junior, Airton |
contributor_str_mv |
Silva, Nádia Félix Felipe da Camilo Junior, Celso Gonçalves Silva, Nádia Félix Felipe da Camilo Junior, Celso Gonçalves Rosa, Thierson Couto Covões, Thiago Ferreira Fernandes, Deborah Silva Alves |
dc.subject.por.fl_str_mv |
Análise de sentimentos Mineração de opiniões Programação genética Classificadores |
topic |
Análise de sentimentos Mineração de opiniões Programação genética Classificadores Sentiment analysis Opinion mining Genetic programming Classifiers CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.eng.fl_str_mv |
Sentiment analysis Opinion mining Genetic programming Classifiers |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
The Web is commonly used as a platform for debates, opinions, evaluations, etc. These data allowed the area of Sentiment Analysis (SA) to develop to extract information and knowledge that can be used in different applications. Among the challenges of SA we can highlight the creation of classifiers with good efficacy. Typically, the classification models are generated using specific heuristics, manually defined and not adaptable to different contexts. Thus, this work proposes the automated generation of hybrid SA classifiers - with Machine Learning (ML) techniques and lexical dictionaries - using Genetic Programming (GP). It is expected to reduce the cost of generating the classifiers and increase the predictive power for each domain analyzed. The goal is that these classifiers will be competitive with the classical ML algorithms used in SA, generalizable, adaptable to the context and able to determine the relevance of each lexical to the applied domain. In addition, the aim is allow to aggregate other ML techniques to create even more effective hybrid solutions. In order to validate the proposal, SemEval 2014 benchmark was used. The results show that the approach with GP is promising since the generated models are competitive, and sometimes better, with other researches. The ensemble proved to be effective in increasing the predictive power of the system, obtaining better results than the use of the techniques individually. Finally, we highlight the ability of models customization according to the context approached and the possibility of knowledge transfer of the users through the functions used by GP. |
publishDate |
2018 |
dc.date.issued.fl_str_mv |
2018-12-14 |
dc.date.accessioned.fl_str_mv |
2019-01-09T11:18:52Z |
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.citation.fl_str_mv |
BORDIN JUNIOR, A. Aplicação de programação genética na análise de sentimentos. 2018. 142 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2018. |
dc.identifier.uri.fl_str_mv |
http://repositorio.bc.ufg.br/tede/handle/tede/9211 |
dc.identifier.dark.fl_str_mv |
ark:/38995/001300000b84q |
identifier_str_mv |
BORDIN JUNIOR, A. Aplicação de programação genética na análise de sentimentos. 2018. 142 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2018. ark:/38995/001300000b84q |
url |
http://repositorio.bc.ufg.br/tede/handle/tede/9211 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
-3303550325223384799 |
dc.relation.confidence.fl_str_mv |
600 600 600 600 |
dc.relation.department.fl_str_mv |
-7712266734633644768 |
dc.relation.cnpq.fl_str_mv |
3671711205811204509 |
dc.relation.sponsorship.fl_str_mv |
-2555911436985713659 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.publisher.program.fl_str_mv |
Programa de Pós-graduação em Ciência da Computação (INF) |
dc.publisher.initials.fl_str_mv |
UFG |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Instituto de Informática - INF (RG) |
publisher.none.fl_str_mv |
Universidade Federal de Goiás |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFG instname:Universidade Federal de Goiás (UFG) instacron:UFG |
instname_str |
Universidade Federal de Goiás (UFG) |
instacron_str |
UFG |
institution |
UFG |
reponame_str |
Repositório Institucional da UFG |
collection |
Repositório Institucional da UFG |
bitstream.url.fl_str_mv |
http://repositorio.bc.ufg.br/tede/bitstreams/f11ef502-b860-434d-8b3a-47ac3c23de30/download http://repositorio.bc.ufg.br/tede/bitstreams/77dc6309-5b43-4736-9c6c-5a20eedc8271/download http://repositorio.bc.ufg.br/tede/bitstreams/92bd49b7-1ec7-4a54-967d-2189cee9bafb/download http://repositorio.bc.ufg.br/tede/bitstreams/d544cef1-cb91-42c5-839a-9c473ecdf2bc/download http://repositorio.bc.ufg.br/tede/bitstreams/445fab3c-9d3a-42ff-9547-443b597f4dd7/download |
bitstream.checksum.fl_str_mv |
bd3efa91386c1718a7f26a329fdcb468 4afdbb8c545fd630ea7db775da747b2f d41d8cd98f00b204e9800998ecf8427e d41d8cd98f00b204e9800998ecf8427e ce3cc567ea43be5719b609ec785f5200 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFG - Universidade Federal de Goiás (UFG) |
repository.mail.fl_str_mv |
tasesdissertacoes.bc@ufg.br |
_version_ |
1815172619740119040 |