Predição da evasão estudantil: uma análise comparativa de diferentes representações de treino na aprendizagem de modelos genéricos

Colpo, Miriam Pizzatto; Primo, Tiago Thompsen; Aguiar, Marilton Sanchotene de

doi:10.5753/sbie.2021.218517

Cited by 3 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thus, to boost the learning process, we collected several records/samples per student, one for each semester attended. This decision was based on a preliminary empirical evaluation inspired by Solis et al (2018), and published in Colpo et al (2021). It is based on the understanding that dropout tends to be a continuous process, rather than an isolated or momentary cause.…”

Section: Methodsmentioning

confidence: 99%

“…In Colpo et al (2021) we used the same data sets for another investigation, which aimed to evaluate different ways of representing dropout behaviour for building prediction models. 2 https://pandas.pydata.org 3 https://sciki t-learn.org4 The first letter of each attribute indicates its aspect: a -academic, c -contextual, d -demographic/social, e -economic, i -interactional.5 Actions refer to all student activities logged by the VLE, which may include, for example, performing access, listing, altering, responding, submitting and removing on entities such as classes, class topics, grades, attendance, content, files, polls, forums, quizzes, tasks, among others.…”

mentioning

confidence: 99%

“… 1 1 In Colpo et al (2021) we used the same data sets for another investigation, which aimed to evaluate different ways of representing dropout behaviour for building prediction models. …”

mentioning

confidence: 99%

See 2 more Smart Citations

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

Self Cite

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: Methodsmentioning

confidence: 99%

mentioning

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Por exemplo, trabalhos que tratam a previsão de desempenho de estudantes [Silva et al 2022, Costa et al 2015, trajetórias [ Êrica Carmo et al 2022], previsão somente com dados acadêmicos e situac ¸ão no curso [Santos et al 2021] predic ¸ão de reprovac ¸ão em disciplinas [de Jesus et al 2021]. Ainda, encontram-se trabalhos que auxiliam na identificac ¸ão de estudantes propensos ao abandono do curso [Kantorski et al 2016, Hortêncio Filho et al 2020, Alyahyan and Düs ¸tegör 2020, Colpo et al 2021, Viana et al 2022. Geralmente, esses trabalhos utilizam técnicas de descoberta de conhecimento em bases de dados ou minerac ¸ão de dados para realizar a previsão de resultados.…”

Section: Trabalhos Relacionadosunclassified

“…O tra-balho de [ Êrica Carmo et al 2022] analisa trajetórias dos alunos evadidos e concluintes em disciplinas do curso de ciência da computac ¸ão e identifica que ambos os grupos (evadidos e concluintes) percorrem as disciplinas do curso de maneira diversa, não obedecendo à matriz curricular proposta. Os trabalhos de [Alyahyan and Düs ¸tegör 2020] e [Colpo et al 2021] abordam revisão sistemática de literatura e uso de melhores práticas encontradas em trabalhos de previsão por meio de MDE.…”

Section: Trabalhos Relacionadosunclassified

Mineração de Dados Educacionais para Predição da Evasão em Cursos de Graduação Presenciais no Ensino Superior

Kantorski,

Martins,

Balejo

et al. 2023

Anais Do XXXIV Simpósio Brasileiro De Informática Na Educação (SBIE 2023)

View full text Add to dashboard Cite

A evasão de alunos nos cursos de graduação tem sido uma das questões relevantes para a gestão acadêmica das Instituições de Ensino Superior. Este artigo apresenta uma análise de vários métodos de aprendizagem de máquina para a predição da evasão em cursos de graduação presenciais. Várias estratégias de aprendizagem de máquina são propostas combinadas com técnicas de ciência de dados e uma ferramenta de business intelligence. Os experimentos foram realizados com os dados de 106 cursos de graduação durante três semestres, envolvendo diversas áreas de conhecimento.

show abstract

Educational Data Mining for Dropout Prediction: Trends, Opportunities, and Challenges

Colpo,

Thompsen Primo,

Aguiar

et al. 2024

RBIE

View full text Add to dashboard Cite

Today, we face academic, social, and economic losses associated with student dropouts. Several studies have applied data mining techniques to educational datasets to understand dropout profiles and recognize at-risk students. To identify the contextual (academic levels, modalities, and systems), technical (tasks, categories of algorithms, and tools), and data (types, coverage, and volume) characteristics related to these works, we performed a systematic literature review, considering institutional and academic degree dropout. Internationally recognized repositories were searched, and the selected articles demonstrated, among other characteristics, a greater exploration of educational, demographic, and economic data of undergraduate students from classification techniques of decision tree ensembles. In addition to not having identified any study from underdeveloped countries among the selected ones, we found shortcomings in the application of predictive models and in making their predictions available to academic managers, which suggests an underutilization of the efforts and potential of most of these studies in educational practice.

show abstract

Predição da evasão estudantil: uma análise comparativa de diferentes representações de treino na aprendizagem de modelos genéricos

Cited by 3 publications

References 10 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

Mineração de Dados Educacionais para Predição da Evasão em Cursos de Graduação Presenciais no Ensino Superior

Educational Data Mining for Dropout Prediction: Trends, Opportunities, and Challenges

Contact Info

Product

Resources

About