Neural Network-Based Collaborative Filtering for Question Sequencing
This work addresses personalized learning for students in e-learning systems, but it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of generating personalized question sequences in e-learning systems by applying Neural Collaborative Filtering (NCF), which achieved an Average Precision correlation score of 0.85, outperforming the EduRank model's 0.8.
E-Learning systems (ELS) and Intelligent Tutoring Systems (ITS) play a significant part in today's education programs. Sequencing questions is the art of generating a personalized quiz for a target learner. A personalized test will enrich the learner's experience and will contribute to a more effective and efficient learning process. In this paper, we used the Neural Collaborative Filtering (NCF) model to generate question sequencing and compare it to a pair-wise memory-based question sequencing algorithm - EduRank. The NCF model showed significantly better ranking results than the EduRank model with an Average precision correlation score of 0.85 compared to 0.8.