End-to-End Deep Knowledge Tracing by Learning Binary Question Embedding

Hiromi Nakagawa, Kaoru Nasuno, Yusuke Iwasawa, Katsuya Uenoyama, Yutaka Matsuo

Abstract: Recent advancements in computer-assisted learning systems have increased the research of knowledge tracing, which estimates student proficiency. In this context, the method called Deep Knowledge Tracing (DKT) shows remarkable performance; however, existing DKT requires human labeling of required skills to solve a question. This limits the optimization of modeling student proficiency and application to real-world data, which are often not well-organized. In this paper, we propose an end-to-end DKT model, which does not depend on any human labeling. Using two datasets, we empirically validated that the learned tags show the same or better performance on DKT and have an information-efficient structure. These results show the potential of our proposed method to enhance the applicable scope and effectiveness of DKT, which could help improve the learning experience of students in more diverse environments.

TL;DR: This paper provides an end-to-end Deep Knowledge Tracing model, which requires no human labeling and enhances the potential of knowledge tracing.

Keywords: Knowledge tracing, Deep Knowledge Tracing, Binary embedding, Educational data mining, Learning sciences