On the Way to Explainable Course Recommendation: Enriching Graph-Based Modeling with Sequential Signals

Course recommendation systems (CRS) play a crucial role in guiding university students through their academic journey by assisting in course selection. Oftentimes, models function as black boxes, offering little transparency in their decisions and limiting students’ trust and adoption of CRS. To address this, we propose Twiner, which captures sequential patterns at two complementary levels: within the knowledge graph itself and through a recurrent model. This dual infusion enables richer contextual modeling in domains where the sequential nature of the data plays an important role. Our approach integrates graph attention networks (GAT) to model complex relationships, including sequential ones between items, and gated recurrent units (GRU) to capture sequential patterns in students’ course-taking behavior across semesters. For explainability, we leverage the attention weights from the GAT module to provide path-reasoning-based justifications. We conduct experiments on four real-world datasets in the domains of course recommendation in higher education, online learning platforms, and grocery shopping. We show that our Twiner model performs similarly to or better than existing state-of-the-art models while also enabling richer explanations. Our findings highlight a transparent and effective solution in which explainability does not sacrifice performance.