Predição da evasão acadêmica aplicando análise temporal
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFG |
Texto Completo: | http://repositorio.bc.ufg.br/tede/handle/tede/11793 |
Resumo: | Academic dropout in higher education is a recurring problem in the daily life of public and private, national and international educational institutions. When a student drops out, this generates consequences in the social, professional, and financial domains both for him/her and for the academic environment where he/she is inserted, which reflects on the national development. Computational methods to assist in predicting cases are an important tool for dealing with this phenomenon. However, student progress is an activity that takes place over time, turning dropout prediction into a temporal problem, and this aspect has been little explored in the literature. The present work aims to contribute to filling this gap, by adapting and expanding a temporal predictive approach that combines unsupervised and supervised learning to predict dropout in the context of Brazilian federal universities. Furthermore, a new method of data segmentation in training and testing is experimented that seeks to reflect, more effectively, the real and temporal scenario of dropout prediction. The approach is tested on a set of supervised machine learning algorithms and evaluated using data extracted from two academic units of the Universidade Federal de Goiás (UFG), between the years 2009 and 2020. It is observed, in the end, that the temporal approach of both the method and the data segmentation provide more realistic results. |
id |
UFG-2_70149d0c64a737c057e8b77be490ece7 |
---|---|
oai_identifier_str |
oai:repositorio.bc.ufg.br:tede/11793 |
network_acronym_str |
UFG-2 |
network_name_str |
Repositório Institucional da UFG |
repository_id_str |
|
spelling |
Nascimento, Hugo Alexandre Dantas dohttp://lattes.cnpq.br/2920005922426876Monsueto, Sandro Eduardohttp://lattes.cnpq.br/5484881117429853Nascimento, Hugo Alexandre Dantas doMonsueto, Sandro EduardoFerreira, Deller JamesMello, Rafael Ferreira Leite dehttp://lattes.cnpq.br/1011398648395279Vieira, Raphael dos Santos Guedes2021-12-28T10:46:05Z2021-12-28T10:46:05Z2021-10-21GUEDES, Raphael. Predição da evasão acadêmica aplicando análise temporal. 2021. 97 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021.http://repositorio.bc.ufg.br/tede/handle/tede/11793Academic dropout in higher education is a recurring problem in the daily life of public and private, national and international educational institutions. When a student drops out, this generates consequences in the social, professional, and financial domains both for him/her and for the academic environment where he/she is inserted, which reflects on the national development. Computational methods to assist in predicting cases are an important tool for dealing with this phenomenon. However, student progress is an activity that takes place over time, turning dropout prediction into a temporal problem, and this aspect has been little explored in the literature. The present work aims to contribute to filling this gap, by adapting and expanding a temporal predictive approach that combines unsupervised and supervised learning to predict dropout in the context of Brazilian federal universities. Furthermore, a new method of data segmentation in training and testing is experimented that seeks to reflect, more effectively, the real and temporal scenario of dropout prediction. The approach is tested on a set of supervised machine learning algorithms and evaluated using data extracted from two academic units of the Universidade Federal de Goiás (UFG), between the years 2009 and 2020. It is observed, in the end, that the temporal approach of both the method and the data segmentation provide more realistic results.A evasão acadêmica no ensino superior é um problema recorrente no cotidiano das instituições de ensino públicas e privadas, nacionais e internacionais. Quando um aluno evade, consequências na esfera social, profissional e financeira são geradas tanto para ele quanto ao ambiente acadêmico onde está inserido, o que reflete no desenvolvimento nacional. Métodos computacionais para auxiliar na predicação dos casos constituem uma importante ferramenta para o tratamento do fenômeno. No entanto, o progresso do discente é uma atividade que acontece ao longo do tempo, fazendo com que a predição da evasão seja um problema de natureza temporal, aspecto este que tem sido pouco explorado na literatura. O presente trabalho se propõe a contribuir para preencher tal lacuna, realizando a adaptação e expansão de uma abordagem preditiva temporal que combina aprendizagem não-supervisionada e supervisionada para predizer a evasão no contexto das universidades federais brasileiras. Adicionalmente, é experimentada uma nova forma de segmentação de dados em treino e teste que busca refletir, com maior efetividade, o cenário real e temporal da predição da evasão. A abordagem é experimentada com um conjunto de algoritmos de aprendizagem de máquina supervisionados e avaliada utilizando dados extraídos de duas unidades acadêmicas da Universidade Federal de Goiás (UFG), entre os anos de 2009 e 2020. É observado, ao final, que a abordagem temporal tanto do método quanto da segmentação dos dados provê resultados mais realistas.Submitted by Onia Arantes Albuquerque (onia.ufg@gmail.com) on 2021-12-02T23:26:18Z No. of bitstreams: 2 Dissertacao - Raphael dos Santos Guedes Vieira - 2021.pdf: 3605528 bytes, checksum: 389ac1ba6583d459448dd7c850dc6f11 (MD5) license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5)Rejected by Luciana Ferreira (lucgeral@gmail.com), reason: Falta o lattes do coorientador. Veja no site do lattes como aparece a primeira forma em Nome em citações bibliográficas VIEIRA, R. S. G on 2021-12-27T15:34:11Z (GMT)Submitted by Onia Arantes Albuquerque (onia.ufg@gmail.com) on 2021-12-27T16:14:21Z No. of bitstreams: 2 license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5) Dissertacao - Raphael dos Santos Guedes Vieira - 2021.pdf: 3605528 bytes, checksum: 389ac1ba6583d459448dd7c850dc6f11 (MD5)Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2021-12-28T10:46:05Z (GMT) No. of bitstreams: 2 license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5) Dissertacao - Raphael dos Santos Guedes Vieira - 2021.pdf: 3605528 bytes, checksum: 389ac1ba6583d459448dd7c850dc6f11 (MD5)Made available in DSpace on 2021-12-28T10:46:05Z (GMT). No. of bitstreams: 2 license_rdf: 805 bytes, checksum: 4460e5956bc1d1639be9ae6146a50347 (MD5) Dissertacao - Raphael dos Santos Guedes Vieira - 2021.pdf: 3605528 bytes, checksum: 389ac1ba6583d459448dd7c850dc6f11 (MD5) Previous issue date: 2021-10-21Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPESporUniversidade Federal de GoiásPrograma de Pós-graduação em Ciência da Computação (INF)UFGBrasilInstituto de Informática - INF (RG)Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessPredição da evasão acadêmicaDivisão temporalMineração de dados educacionaisTemporal learning analyticsAcademic dropout predictionTemporal splitEducational data miningTemporal learning analyticsCIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOPredição da evasão acadêmica aplicando análise temporalPrediction of academic dropout applying time analyticsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis20500500500500261841reponame:Repositório Institucional da UFGinstname:Universidade Federal de Goiás (UFG)instacron:UFGORIGINALDissertacao - Raphael dos Santos Guedes Vieira - 2021.pdfDissertacao - Raphael dos Santos Guedes Vieira - 2021.pdfapplication/pdf3605528http://repositorio.bc.ufg.br/tede/bitstreams/537d3222-a28a-4e8c-93f3-39b4f880e326/download389ac1ba6583d459448dd7c850dc6f11MD53LICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://repositorio.bc.ufg.br/tede/bitstreams/d137bd41-d731-422b-bad7-e3935d5c9b12/download8a4605be74aa9ea9d79846c1fba20a33MD54CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805http://repositorio.bc.ufg.br/tede/bitstreams/f9f80d72-db7e-4b06-b3eb-675b0df82d31/download4460e5956bc1d1639be9ae6146a50347MD55tede/117932021-12-28 07:46:05.615http://creativecommons.org/licenses/by-nc-nd/4.0/Attribution-NonCommercial-NoDerivatives 4.0 Internationalopen.accessoai:repositorio.bc.ufg.br:tede/11793http://repositorio.bc.ufg.br/tedeRepositório InstitucionalPUBhttp://repositorio.bc.ufg.br/oai/requesttasesdissertacoes.bc@ufg.bropendoar:2021-12-28T10:46:05Repositório Institucional da UFG - Universidade Federal de Goiás (UFG)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 |
dc.title.pt_BR.fl_str_mv |
Predição da evasão acadêmica aplicando análise temporal |
dc.title.alternative.eng.fl_str_mv |
Prediction of academic dropout applying time analytics |
title |
Predição da evasão acadêmica aplicando análise temporal |
spellingShingle |
Predição da evasão acadêmica aplicando análise temporal Vieira, Raphael dos Santos Guedes Predição da evasão acadêmica Divisão temporal Mineração de dados educacionais Temporal learning analytics Academic dropout prediction Temporal split Educational data mining Temporal learning analytics CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
title_short |
Predição da evasão acadêmica aplicando análise temporal |
title_full |
Predição da evasão acadêmica aplicando análise temporal |
title_fullStr |
Predição da evasão acadêmica aplicando análise temporal |
title_full_unstemmed |
Predição da evasão acadêmica aplicando análise temporal |
title_sort |
Predição da evasão acadêmica aplicando análise temporal |
author |
Vieira, Raphael dos Santos Guedes |
author_facet |
Vieira, Raphael dos Santos Guedes |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Nascimento, Hugo Alexandre Dantas do |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/2920005922426876 |
dc.contributor.advisor-co1.fl_str_mv |
Monsueto, Sandro Eduardo |
dc.contributor.advisor-co1Lattes.fl_str_mv |
http://lattes.cnpq.br/5484881117429853 |
dc.contributor.referee1.fl_str_mv |
Nascimento, Hugo Alexandre Dantas do |
dc.contributor.referee2.fl_str_mv |
Monsueto, Sandro Eduardo |
dc.contributor.referee3.fl_str_mv |
Ferreira, Deller James |
dc.contributor.referee4.fl_str_mv |
Mello, Rafael Ferreira Leite de |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/1011398648395279 |
dc.contributor.author.fl_str_mv |
Vieira, Raphael dos Santos Guedes |
contributor_str_mv |
Nascimento, Hugo Alexandre Dantas do Monsueto, Sandro Eduardo Nascimento, Hugo Alexandre Dantas do Monsueto, Sandro Eduardo Ferreira, Deller James Mello, Rafael Ferreira Leite de |
dc.subject.por.fl_str_mv |
Predição da evasão acadêmica Divisão temporal Mineração de dados educacionais Temporal learning analytics |
topic |
Predição da evasão acadêmica Divisão temporal Mineração de dados educacionais Temporal learning analytics Academic dropout prediction Temporal split Educational data mining Temporal learning analytics CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
dc.subject.eng.fl_str_mv |
Academic dropout prediction Temporal split Educational data mining Temporal learning analytics |
dc.subject.cnpq.fl_str_mv |
CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO |
description |
Academic dropout in higher education is a recurring problem in the daily life of public and private, national and international educational institutions. When a student drops out, this generates consequences in the social, professional, and financial domains both for him/her and for the academic environment where he/she is inserted, which reflects on the national development. Computational methods to assist in predicting cases are an important tool for dealing with this phenomenon. However, student progress is an activity that takes place over time, turning dropout prediction into a temporal problem, and this aspect has been little explored in the literature. The present work aims to contribute to filling this gap, by adapting and expanding a temporal predictive approach that combines unsupervised and supervised learning to predict dropout in the context of Brazilian federal universities. Furthermore, a new method of data segmentation in training and testing is experimented that seeks to reflect, more effectively, the real and temporal scenario of dropout prediction. The approach is tested on a set of supervised machine learning algorithms and evaluated using data extracted from two academic units of the Universidade Federal de Goiás (UFG), between the years 2009 and 2020. It is observed, in the end, that the temporal approach of both the method and the data segmentation provide more realistic results. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-12-28T10:46:05Z |
dc.date.available.fl_str_mv |
2021-12-28T10:46:05Z |
dc.date.issued.fl_str_mv |
2021-10-21 |
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.citation.fl_str_mv |
GUEDES, Raphael. Predição da evasão acadêmica aplicando análise temporal. 2021. 97 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021. |
dc.identifier.uri.fl_str_mv |
http://repositorio.bc.ufg.br/tede/handle/tede/11793 |
identifier_str_mv |
GUEDES, Raphael. Predição da evasão acadêmica aplicando análise temporal. 2021. 97 f. Dissertação (Mestrado em Ciência da Computação) - Universidade Federal de Goiás, Goiânia, 2021. |
url |
http://repositorio.bc.ufg.br/tede/handle/tede/11793 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
20 |
dc.relation.confidence.fl_str_mv |
500 500 500 500 |
dc.relation.department.fl_str_mv |
26 |
dc.relation.cnpq.fl_str_mv |
184 |
dc.relation.sponsorship.fl_str_mv |
1 |
dc.rights.driver.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ |
eu_rights_str_mv |
openAccess |
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/537d3222-a28a-4e8c-93f3-39b4f880e326/download http://repositorio.bc.ufg.br/tede/bitstreams/d137bd41-d731-422b-bad7-e3935d5c9b12/download http://repositorio.bc.ufg.br/tede/bitstreams/f9f80d72-db7e-4b06-b3eb-675b0df82d31/download |
bitstream.checksum.fl_str_mv |
389ac1ba6583d459448dd7c850dc6f11 8a4605be74aa9ea9d79846c1fba20a33 4460e5956bc1d1639be9ae6146a50347 |
bitstream.checksumAlgorithm.fl_str_mv |
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_ |
1798044424676048896 |