Multi-View MOOC Quality Evaluation via Information-Aware Graph Representation Learning

In this paper, we study the problem of MOOC quality evaluation that is essential for improving course materials, promoting students' learning efficiency, and benefiting user services. While achieving promising performances, current works still suffer from complicated interactions relationships entities in platforms. To tackle challenges, formulate as a representation task based, develop an Information-aware Graph Representation Learning(IaGRL) multi-view evaluation. Specifically, We first build Heterogeneous Network (HIN) to represent among And then decompose HIN into multiple single-relation graphs based on meta-paths depict semantics courses. The can be further converted graph task. Different traditional learning, learned representations are expected match following three types validity: (1) agreement expressiveness between raw portfolio representations; (2) consistency each view unified (3) alignment platform representations. Therefore, propose exploit mutual information preserving validity conduct extensive experiments over real-world datasets demonstrate effectiveness our proposed method.