Abstract
Thanks to the advances in digital educational technology, online learning (or e-learning) environments such as Massive Open Online Course (MOOC) have been rapidly growing. In the online educational systems, however, there are two inherent challenges in predicting performance of students and providing personalized supports to them: sparse data and cold-start problem. To overcome such challenges, this article aims to employ a pertinent machine learning algorithm, the Bayesian Probabilistic Matrix Factorization (BPMF) that can enhance the prediction by incorporating background information on the side of students and/or items. An experimental study with two prediction settings was conducted to apply the BPMF to the Statistics Online data. The results shows that the BPMF with using side information provided more accurate prediction in the performance of both existing and new students on items, compared to the algorithm without using any side information. When the data are sparse, it is demonstrated that a lower dimensional solution of the BPMF would benefit the prediction accuracy. Lastly, the applicability of the BPMF to the online educational systems were discussed in the context of educational assessment.
Highlights
Digital educational technology has advanced considerably over the last few decades
Evaluation Method For each data set, the prediction performance of the Bayesian Probabilistic Matrix Factorization (BPMF) is evaluated by a 10-fold cross validation (CV)
To evaluate the accuracy of the predictions made by our system, we employed Receiver Operating Characteristic (ROC) curves and Area under the Receiver Operating Characteristic (AUROC)
Summary
Online learning (or e-learning) environments such as Massive Open Online Course (MOOC) have been rapidly growing and getting attention. Such online educational systems have promising advantages in helping students access more to the qualified instructions and resources as well as in allowing them to manage their learning process flexibly (Zhang & Chang, 2015). The systems are often incapable of correctly matching the new students with the incipient items due to the lack of background information for each student, which results in inaccuracy of item recommendations (and a lot of dropout) at the beginning of online learning, which is called the ‘cold-start’ problem (Bobadilla et al, 2012)
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call