Mineração de dados auxiliando na descoberta das causas da evasão escolar: Um Mapeamento Sistemático da Literatura

Marques, Leonardo Torres; Castro, Angélica Félix de; Marques, Bruno Torres; Silva, Jesaı́as Carvalho Pereira; Queiroz, Paulo Gabriel Gadelha

doi:10.22456/1679-1916.99470

Cited by 3 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thus, in order to discover, in a more generalizable way, patterns related to dropout and/or the prediction of this phenomenon, there has been a growing development of studies that applies ML and EDM techniques to large volumes of educational data, made available by academic management systems and Virtual Learning Environments (VLEs). Marques et al (2019), Mduma et al (2019) and Colpo et al (2020) presented reviews and research mappings that explore ML and EDM techniques in the analysis and prediction of student dropout. While the first two studies consider the international scenario, the last one focuses on the Brazilian context.…”

Section: Related Workmentioning

confidence: 99%

“…In addition to considering student performance data before and during the pandemic, as Gonzalez et al (2020), Iglesias‐Pradas et al (2021), El Said (2021) and Takács et al (2023), we consider other academic, contextual, economic, interactional and demographic data of students in our analysis. We adopt classification techniques, as well as much of the research explored in Marques et al (2019), Mduma et al (2019), and Colpo et al (2020), to build interpretable predictive models of dropout based on data preceding and succeeding the start of the ERL. By comparing these models, we analyse the differences between the characteristics of dropout pre‐ and during‐pandemic patterns.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Lessons learned from the student dropout patterns on COVID‐19 pandemic: An analysis supported by machine learning

Colpo,

Primo,

de Aguiar

2023

Brit J Educational Tech

View full text Add to dashboard Cite

During the COVID‐19 pandemic, the challenges associated with the transition from face‐to‐face to emergency remote education increased concerns about student dropout. Aligned with this concern, this study investigates the impact of the pandemic on the dropout patterns of 3371 undergraduate students from a Brazilian institution. Using data mining and machine learning techniques, we developed predictive dropout models based on student data preceding and succeeding the onset of the pandemic. Through the interpretation and comparison of these models and with the support of statistical and graphical analyses, we identify that the patterns persistently indicate that young students in their initial semesters, characterized by lower income, academic performance, and interaction, remain most susceptible to dropping out. Despite the pandemic leading to an enhanced predictive capability of data regarding student interaction within the virtual learning environment, our analysis revealed a lack of significant variation in dropout patterns. Institutionally, this indicates that a considerable number of dropouts likely encountered challenges in adapting to higher education, both before and throughout the pandemic. Practitioner notesWhat is already known about this topic The challenges posed by emergency remote learning, implemented during the COVID‐19 pandemic, may exacerbate the dropout problem and change the patterns involved in this phenomenon. Despite being widely used to identify dropout profiles and/or predict at‐risk students, data mining and machine learning techniques have been little explored in the investigation of changes associated with the pandemic context. What this paper adds We employ data mining and machine learning techniques to construct predictive and interpretable dropout models for the pre‐ and during‐pandemic contexts of a Brazilian institution. Comparing these models, we investigate the impacts of the pandemic on dropout patterns. The pandemic and the shift to emergency remote learning have an enhanced predictive capability of data regarding student interaction within the virtual learning environment. Throughout the pandemic, there was limited variation observed in dropout patterns, consistently highlighting young students in their initial semesters with lower income, academic performance and levels of interaction. Implications for practice and/or policy This study urges the inclusion of interactional student data in future dropout prediction research, capitalizing on the enhanced predictive power attained through the widespread adoption of virtual learning environments. Institutionally, the dropout patterns from before and during the pandemic suggest that students may be facing difficulties in adapting to higher education. In addition to the need to intensify preventive actions, this work indicates the need to conduct a study specifically targeting first‐semester students to understand their needs better and redesign preventive policies.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Lessons learned from the student dropout patterns on COVID‐19 pandemic: An analysis supported by machine learning

Colpo,

Primo,

de Aguiar

2023

Brit J Educational Tech

View full text Add to dashboard Cite

show abstract

“…Em um estudo de revisão sistemática da literatura realizada por [Agrusti et al 2019], verificou-se que dos 73 trabalhos de minerac ¸ão de dados na previsão de evasão estudantil, 67% usaram o classificador Árvore de Decisão, seguido pela classificac ¸ão bayesiana com 49%. Outro mapeamento sistemático foi realizado por [Torres Marques et al 2019], verificando que técnicas de classificac ¸ão vêm sendo altamente utilizadas na detecc ¸ão de evasão escolar devido à alta precisão nas previsões, listando como os algoritmos mais utilizados: naive bayes (NB), support-vector machine (SVM), network of radial basis function (RBFNetwork), multilayer perceptron (MLP), k-nearest neigh-bours (IBk), Jrip, OneR, J48, PART e AdaBoostM1. Além disso, verificou-se também as ferramentas de minerac ¸ão de dados mais utilizadas como sendo o Weka 1 no quesito evasão.…”

Section: Trabalhos Relacionadosunclassified

Avaliação de Classificadores para Predição de Evasão no Ensino Superior Utilizando Janela Semestral

Viana

Santana

Rabêlo

2022

Anais Do XXXIII Simpósio Brasileiro De Informática Na Educação (SBIE 2022)

View full text Add to dashboard Cite

O alto índice de evasão nas Instituições Federais de Ensino Superior (IFES) é um fenômeno que, cada vez mais, vêm preocupando docentes e gestores educacionais. Neste sentido, estratégias como Mineração de Dados Educacionais vêm sendo usadas para mitigar esse problema. Uma proposta para classificação de alunos Evadidos e Graduados é apresentada nesse trabalho, gerando modelos treinados para cada janela semestral. Os experimentos foram realizados com dados dos cursos de Computação e Sistemas de Informação da Universidade Federal do Piauí (UFPI). Os resultados do processo de Mineração são promissores com acurácias de 85% e 96%.

show abstract

A Model of Actions to Reduce Evasion in Higher Technology Courses : An Experience Report

Rocha¹,

Vanderlei²,

Araújo

et al. 2021

2021 16th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

Mineração de dados auxiliando na descoberta das causas da evasão escolar: Um Mapeamento Sistemático da Literatura

Cited by 3 publications

References 5 publications

Lessons learned from the student dropout patterns on COVID‐19 pandemic: An analysis supported by machine learning

Lessons learned from the student dropout patterns on COVID‐19 pandemic: An analysis supported by machine learning

Avaliação de Classificadores para Predição de Evasão no Ensino Superior Utilizando Janela Semestral

A Model of Actions to Reduce Evasion in Higher Technology Courses : An Experience Report

Contact Info

Product

Resources

About