Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

Researchers propose MR-ConceptGCN, a multi-relational graph convolutional network approach for sequential learner modeling, combining personal knowledge graphs and pre-trained language models. The method is evaluated in an online user study with 31 participants, demonstrating benefits in accuracy, usefulness, and user satisfaction. MR-ConceptGCN enhances relation- and semantic-aware representations.