Integrating courses' relationship into predicting student performance

Abstract

In Intelligent Tutoring System (ITS) as well as the E-learning system at the university, predicting student learning performance to suggest courses is an essential task of an academic advisor. Many kinds of research address to solve this problem with diverse approaches such as classification, regression, association rules, and recommender systems. Recently, it was a measurable success in using collaborative filtering in the recommender system, especially the matrix factorization technique, to build the courses' recommendation system. There are many advances to improve the accuracy of the prediction, such as using student profiles, course properties, or course relationships; however, they have not been mined. This study proposes an approach which integrates the course relationships into the courses' recommendation system to improve the prediction accuracy. Experimental results of the proposed approach are positive when we validate the published educational datasets.

EKT: Exercise-Aware Knowledge Tracing for Student Performance Prediction

“…To improve prediction results, Thai et al proposed MRMF to explore the multiple relationships between students, exercises, and knowledge concepts by MF techniques [26]. Similarly, CRMF integrated the course relationships to update representations of exercises [15]. Moreover, researchers were inspired by social recommendation systems and used the SocialMF technique to improve the prediction accuracy [27].…”

“…• NeuralCDM [28]: This is an improved multi-dimensional cognitive diagnosis model that utilizes neural networks as the interaction function. • CRMF [15]: This MF based model takes knowledge concepts into consideration by assuming that representations of exercises with the same knowledge concepts are more similar. • R-GCN [23]: A substructure of our model that only uses R-GCN to predict scores but neglects students' proficiency on knowledge concepts.…”

Deep Biased Matrix Factorization for Student Performance Prediction

“…In the current landscape of predicting student performance, a common strategy is to enhance the accuracy of the predictions by utilizing various techniques of Matrix Factorization, including Biased-MF [21], Social-MF [23], and CRMF [24]. These techniques aim to pose an optimization problem by defining an error function that integrates multiple sources of information to evaluate the model's performance.…”

“…In addition, another paper [24] proposed a novel approach for incorporating the relationships between courses (e.g., knowledge/skills) into the MF, which can help to solve the PSP problem. This approach involves gathering information about course relationships and using this information to enrich the recommendation system.…”

“…The problem of predicting student performance has been mapped to a recommendation prediction task in several studies, including [21], [23], [24]. In a recommender system, there are three primary elements: user, item, and rating, where the task is to predict the user's rating for all unrated items and recommend the top-N highest predicted scores.…”