STHKT: Spatiotemporal Knowledge Tracing with Topological Hawkes Process

Shuting Li, Shuanghong Shen, Yu Su, Xinjie Sun, Junyu Lu, Qi Mo, Zhenyi Wu, Qi Liu

Abstract: Highlights•We construct a tripartite heterogeneous graph of concepts–questions–students.•We topologize to connect temporal and structural information in the KT process.•We use two GCN networks to model clustering effect and group effect.•Intensity function in the topological Hawkes process enhances the attention score.•Our method achieves more precise result.