Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.5220/0010972800003179 http://hdl.handle.net/11449/237930 |
Resumo: | Social media sentiment analysis consists on extracting information from users' comments. It can assist the decision-making process of companies, aid public health and security and even identify intentions and opinions about candidates in elections. However, such data come from an environment with big data characteristics, which can make traditional and manual analysis impracticable because of the high dimensionality. The implications on the analysis are high computational cost and low quality of results. Up to date research focuses on how to analyse feelings of users with machine learning and inspired by nature methods. To analyse such data effectively, a feature selection through cuckoo search and genetic algorithm is proposed. Machine learning with lexical analysis has become an attractive alternative to overcome this challenge. This paper aims to present a hybrid bio-inspired approach to realize feature selection and improve sentiment classification quality. The scientific contribution is the improvement of a classification model considering pre-processing of the data with different languages and contexts. The results prove that the developed method enriches the predictive model. There is an improvement of around 13% in accuracy with a 45% average usage of attributes related to traditional analysis. |
id |
UNSP_6b085807dd7e70be920caafeae459542 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/237930 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment AnalysisSentiment AnalysisFeature SelectionCuckoo SearchGenetic AlgorithmMachine LearningSocial MediaSocial media sentiment analysis consists on extracting information from users' comments. It can assist the decision-making process of companies, aid public health and security and even identify intentions and opinions about candidates in elections. However, such data come from an environment with big data characteristics, which can make traditional and manual analysis impracticable because of the high dimensionality. The implications on the analysis are high computational cost and low quality of results. Up to date research focuses on how to analyse feelings of users with machine learning and inspired by nature methods. To analyse such data effectively, a feature selection through cuckoo search and genetic algorithm is proposed. Machine learning with lexical analysis has become an attractive alternative to overcome this challenge. This paper aims to present a hybrid bio-inspired approach to realize feature selection and improve sentiment classification quality. The scientific contribution is the improvement of a classification model considering pre-processing of the data with different languages and contexts. The results prove that the developed method enriches the predictive model. There is an improvement of around 13% in accuracy with a 45% average usage of attributes related to traditional analysis.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Sao Paulo State Univ, UNESP, Inst Biosci, Humanities & Exact Sci Ibilce, Campus Sao Jose do Rio Preto, Sao Paulo, BrazilFluminense Fed Univ UFF, Niteroi, RJ, BrazilSao Paulo State Univ, UNESP, Inst Biosci, Humanities & Exact Sci Ibilce, Campus Sao Jose do Rio Preto, Sao Paulo, BrazilScitepressUniversidade Estadual Paulista (UNESP)Universidade Federal Fluminense (UFF)Silva, Luis Marcello Moraes [UNESP]Valencio, Carlos Roberto [UNESP]Zafalon, Geraldo Francisco Donega [UNESP]Columbini, Angelo CesarFilipe, J.Smialek, M.Brodsky, A.Hammoudi, S.2022-11-30T15:19:54Z2022-11-30T15:19:54Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject297-307http://dx.doi.org/10.5220/0010972800003179Iceis: Proceedings Of The 24th International Conference On Enterprise Information Systems - Vol 1. Setubal: Scitepress, p. 297-307, 2022.http://hdl.handle.net/11449/23793010.5220/0010972800003179WOS:000814767200033Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIceis: Proceedings Of The 24th International Conference On Enterprise Information Systems - Vol 1info:eu-repo/semantics/openAccess2022-11-30T15:19:54Zoai:repositorio.unesp.br:11449/237930Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-11-30T15:19:54Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
title |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
spellingShingle |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis Silva, Luis Marcello Moraes [UNESP] Sentiment Analysis Feature Selection Cuckoo Search Genetic Algorithm Machine Learning Social Media |
title_short |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
title_full |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
title_fullStr |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
title_full_unstemmed |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
title_sort |
Feature Selection with Hybrid Bio-inspired Approach for Classifying Multi-idiom Social Media Sentiment Analysis |
author |
Silva, Luis Marcello Moraes [UNESP] |
author_facet |
Silva, Luis Marcello Moraes [UNESP] Valencio, Carlos Roberto [UNESP] Zafalon, Geraldo Francisco Donega [UNESP] Columbini, Angelo Cesar Filipe, J. Smialek, M. Brodsky, A. Hammoudi, S. |
author_role |
author |
author2 |
Valencio, Carlos Roberto [UNESP] Zafalon, Geraldo Francisco Donega [UNESP] Columbini, Angelo Cesar Filipe, J. Smialek, M. Brodsky, A. Hammoudi, S. |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade Federal Fluminense (UFF) |
dc.contributor.author.fl_str_mv |
Silva, Luis Marcello Moraes [UNESP] Valencio, Carlos Roberto [UNESP] Zafalon, Geraldo Francisco Donega [UNESP] Columbini, Angelo Cesar Filipe, J. Smialek, M. Brodsky, A. Hammoudi, S. |
dc.subject.por.fl_str_mv |
Sentiment Analysis Feature Selection Cuckoo Search Genetic Algorithm Machine Learning Social Media |
topic |
Sentiment Analysis Feature Selection Cuckoo Search Genetic Algorithm Machine Learning Social Media |
description |
Social media sentiment analysis consists on extracting information from users' comments. It can assist the decision-making process of companies, aid public health and security and even identify intentions and opinions about candidates in elections. However, such data come from an environment with big data characteristics, which can make traditional and manual analysis impracticable because of the high dimensionality. The implications on the analysis are high computational cost and low quality of results. Up to date research focuses on how to analyse feelings of users with machine learning and inspired by nature methods. To analyse such data effectively, a feature selection through cuckoo search and genetic algorithm is proposed. Machine learning with lexical analysis has become an attractive alternative to overcome this challenge. This paper aims to present a hybrid bio-inspired approach to realize feature selection and improve sentiment classification quality. The scientific contribution is the improvement of a classification model considering pre-processing of the data with different languages and contexts. The results prove that the developed method enriches the predictive model. There is an improvement of around 13% in accuracy with a 45% average usage of attributes related to traditional analysis. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11-30T15:19:54Z 2022-11-30T15:19:54Z 2022-01-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.5220/0010972800003179 Iceis: Proceedings Of The 24th International Conference On Enterprise Information Systems - Vol 1. Setubal: Scitepress, p. 297-307, 2022. http://hdl.handle.net/11449/237930 10.5220/0010972800003179 WOS:000814767200033 |
url |
http://dx.doi.org/10.5220/0010972800003179 http://hdl.handle.net/11449/237930 |
identifier_str_mv |
Iceis: Proceedings Of The 24th International Conference On Enterprise Information Systems - Vol 1. Setubal: Scitepress, p. 297-307, 2022. 10.5220/0010972800003179 WOS:000814767200033 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Iceis: Proceedings Of The 24th International Conference On Enterprise Information Systems - Vol 1 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
297-307 |
dc.publisher.none.fl_str_mv |
Scitepress |
publisher.none.fl_str_mv |
Scitepress |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803047455754813440 |