Assignments as Influential Factor to Improve the Prediction of Student Performance in Online Courses

Abstract

Studies on the prediction of student success in distance learning have explored mainly demographics factors and student interactions with the virtual learning environments. However, it is remarkable that a very limited number of studies use information about the assignments submitted by students as influential factor to predict their academic achievement. This paper aims to explore the real importance of assignment information for solving students’ performance prediction in distance learning and evaluate the beneficial effect of including this information. We investigate and compare this factor and its potential from two information representation approaches: the traditional representation based on single instances and a more flexible representation based on Multiple Instance Learning (MIL), focus on handle weakly labeled data. A comparative study is carried out using the Open University Learning Analytics dataset, one of the most important public datasets in education provided by one of the greatest online universities of United Kingdom. The study includes a wide set of different types of machine learning algorithms addressed from the two data representation commented, showing that algorithms using only information about assignments with a representation based on MIL can outperform more than 20% the accuracy with respect to a representation based on single instance learning. Thus, it is concluded that applying an appropriate representation that eliminates the sparseness of data allows to show the relevance of a factor, such as the assignments submitted, not widely used to date to predict students’ academic performance. Moreover, a comparison with previous works on the same dataset and problem shows that predictive models based on MIL using only assignments information obtain competitive results compared to previous studies that include other factors to predict students performance.

Virtual and Traditional Lecturing Technique Impact on Dental Education

“…We must not lose sight of the fact that besides theoretical education, dental students must acquire clinical skills to make a correct diagnosis and to correctly execute the necessary treatment [9]. Abbasi et al conducted a study among health science students regarding the perception and satisfaction of virtual learning and most of the students agreed that this learning method was not useful for developing the needed clinical skills [10].…”

SA-FEM: Combined Feature Selection and Feature Fusion for Students’ Performance Prediction

“…Figueroa-Cañas et al [22] proposed a decision-treebased model that relies only on average scores on non-mandatory formative assessments to identify students at risk in terms of dropout and final exam performance. Esteban et al [23] found that using only MIL representation of assignment-related information was more accurate in predicting student academic performance relative to a single-instance learning-based representation. Aydo gdu [24] used artificial neural networks for final student grade prediction through student behavior in navigating and tracking courses in an online learning environment.…”

A utilização de Metodologias Ativas com suporte de Mineração de Dados Educacionais e Learning Analytics para a mitigação da evasão em EaD: um mapeamento sistemático da literatura

“…Em relação a recentes trabalhos, Esteban et al (2021) realizaram um estudo de previsão do desempenho dos alunos baseado na execução de tarefas no ambiente virtual. Os resultados evidenciaram que, em um conjunto de 23 algoritmos de MDE utilizados, os atributos de interação do envio de tarefas foram importantes para a indicação e previsão dos alunos com riscos de evasão.…”

“…Em relação aos 79 algoritmos citados, verificam-se autores que utilizam um ou mais algoritmos para a obtenção dos resultados. Esteban et al (2021), Leite et al (2021) e Kostopoulos et al (2018a), por exemplo, utilizam 18, 14 e 12 algoritmos, respectivamente, com o objetivo de prever o desempenho dos alunos. , Macedo et al (2019), , Whitehill et al (2017), Niu et al (2018), Com o propósito de inovação, novos algoritmos foram desenvolvidos na tentativa de contribuir com a identificação e mitigação da evasão em EaD.…”

“…Existem trabalhos que utilizam as técnicas de Mineração de Dados Educacionais (MDE, do inglês Educational Data Mining -EDM) e Learning Analytics (LA) para identificar alunos propensos a evadirem do curso Liang et al, 2016;Queiroga et al, 2017;Ramos et al, 2018;Ortigosa et al, 2019;Tomasevic et al, 2020;Esteban et al, 2021;Tamada et al, 2022;Tran et al, 2023), no entanto, restritas a tal ação, incapazes de reverter esse Andrade et al RBIE v.31 -2023 1059 cenário (Widyahastuti & Tjhin, 2018). Sendo assim, a tomada de decisão para mitigar esse problema é, normalmente, dependente do professor, que necessita utilizar de metodologias educacionais para resgatar e incentivar o aluno a permanecer no curso.…”