Improving Predictive Modeling for At-Risk Student Identification: A Multistage Approach

Hung, Jui-Long; Shelton, Brett E.; Yang, Juan; Du, Xu

doi:10.1109/tlt.2019.2911072

Cited by 46 publications

(51 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is also important because many articles just consider one course [16], and although some articles, as shown before, have focused on transferring models to other courses, it is also relevant to analyze the generalizability of the predictors. A similar work in this line was made by Hung et al [42], who analyzed this issue in several educational stages, although this article will analyze different contexts within the same stage.…”

Section: Generalizability and Sustainability Of Predictionsmentioning

confidence: 73%

“…In addition, Gitinabard et al [41] analyzed the generalizability in four courses and found accurate results when transferring models, although they were better when the course was the same but in another offering. Furthermore, Hung et al [42] proposed three models to predict successful students and at-risk students and a third model to optimize the thresholds of the previous models. They used K-12 and high-school contexts and found important differences in the context as well as the best predictors.…”

Section: Generalizability and Sustainability Of Predictionsmentioning

confidence: 99%

See 1 more Smart Citation

Generalizing Predictive Models of Admission Test Success Based on Online Interactions

et al. 2019

View full text Add to dashboard Cite

To start medical or dentistry studies in Flanders, prospective students need to pass a central admission test. A blended program with four Small Private Online Courses (SPOCs) was designed to support those students. The logs from the platform provide an opportunity to delve into the learners’ interactions and to develop predictive models to forecast success in the test. Moreover, the use of different courses allows analyzing how models can generalize across courses. This article has the following objectives: (1) to develop and analyze predictive models to forecast who will pass the admission test, (2) to discover which variables have more effect on success in different courses, (3) to analyze to what extent models can be generalized to other courses and subsequent cohorts, and (4) to discuss the conditions to achieve generalizability. The results show that the average grade in SPOC exercises using only first attempts is the best predictor and that it is possible to transfer predictive models with enough reliability when some context-related conditions are met. The best performance is achieved when transferring within the same cohort to other SPOCs in a similar context. The performance is still acceptable in a consecutive edition of a course. These findings support the sustainability of predictive models.

show abstract

Section: Generalizability and Sustainability Of Predictionsmentioning

confidence: 73%

Section: Generalizability and Sustainability Of Predictionsmentioning

confidence: 99%

Generalizing Predictive Models of Admission Test Success Based on Online Interactions

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Early warning prediction studies should provide accurate prediction outcomes at an early stage. However, the previous study [16] pointed that most performance prediction studies utilized aggregated behaviors at the end of semester for predictive modelling. Given that the accumulation levels are different during and at the end of the course, utilizing student accumulated behavioral frequencies at the end of a course cannot perform real prediction to achieve the goal of ''early warning''.…”

Section: Related Work a Early Warning Predictionmentioning

confidence: 99%

“…It usually utilizes online learning activities (i.e. online behaviors or/and discussions) and classification algorithms to fulfill such tasks [6], [9]- [16]. However, traditional classification algorithms, which are normally designed to maximize the overall accuracy, are suitable for balanced datasets rather than imbalanced ones [17], [18], while educational dataset is often highly imbalanced [18], [19].…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, LVAE component mainly aims to learn the latent feature distribution of at-risk students and generate some at-risk samples for the purpose of obtaining a balanced dataset. Due to the outstanding prediction performance of DNN [16], [30], it has been applied to perform final prediction in order to explore whether the latent feature distribution of at-risk students learnt by LVAE component is helpful for accurately identifying and capturing at-risk students. Finally, the effectiveness and robustness of the proposed LVAEPre framework are verified through multiple sets of experiments.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Framework Based on Latent Variational Autoencoder for Providing Early Warning of At-Risk Students

Yang

Hung

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The rapid development of learning technologies has enabled online learning paradigm to gain great popularity in both high education and K-12, which makes the prediction of student performance become one of the most popular research topics in education. However, the traditional prediction algorithms are originally designed for balanced dataset, while the educational dataset typically belongs to highly imbalanced dataset, which makes it more difficult to accurately identify the at-risk students. In order to solve this dilemma, this study proposes an integrated framework (LVAEPre) based on latent variational autoencoder (LVAE) with deep neural network (DNN) to alleviate the imbalanced distribution of educational dataset and further to provide early warning of at-risk students. Specifically, with the characteristics of educational data in mind, LVAE mainly aims to learn latent distribution of at-risk students and to generate at-risk samples for the purpose of obtaining a balanced dataset. DNN is to perform final performance prediction. Extensive experiments based on the collected K-12 dataset show that LVAEPre can effectively handle the imbalanced education dataset and provide much better and more stable prediction results than baseline methods in terms of accuracy and F 1.5 score. The comparison of t-SNE visualization results further confirms the advantage of LVAE in dealing with imbalanced issue in educational dataset. Finally, through the identification of the significant predictors of LVAEPre in the experimental dataset, some suggestions for designing pedagogical interventions are put forward. INDEX TERMS Performance prediction, early warning prediction, latent variational autoencoder, resampling methods, deep neural network, t-SNE.

show abstract

The Dire Cost of Early Disengagement: A Four-Year Learning Analytics Study over a Full Program

Saqr

López-Pernas

2021

Technology-Enhanced Learning for a Free, Safe, and Sustainable World

View full text Add to dashboard Cite

Improving Predictive Modeling for At-Risk Student Identification: A Multistage Approach

Cited by 46 publications

References 35 publications

Generalizing Predictive Models of Admission Test Success Based on Online Interactions

Generalizing Predictive Models of Admission Test Success Based on Online Interactions

An Integrated Framework Based on Latent Variational Autoencoder for Providing Early Warning of At-Risk Students

The Dire Cost of Early Disengagement: A Four-Year Learning Analytics Study over a Full Program

Contact Info

Product

Resources

About