SimStu-Transformer: A Transformer-Based Approach to Simulating Student Behaviour

Li, Zhaoxing; Shi, Lei; Cristea, Alexandra; Zhou, Yunzhan; Xiao, Chenghao; Pan, Ziqi

doi:10.1007/978-3-031-11647-6_67

SimStu-Transformer: A Transformer-Based Approach to Simulating Student Behaviour

Li, Zhaoxing; Shi, Lei; Cristea, Alexandra; Zhou, Yunzhan; Xiao, Chenghao; Pan, Ziqi

Authors

Zhaoxing Li zhaoxing.li2@durham.ac.uk
PGR Student Doctor of Philosophy

Lei Shi

Professor Alexandra Cristea alexandra.i.cristea@durham.ac.uk
Professor

Yunzhan Zhou yunzhan.zhou@durham.ac.uk
PGR Student Doctor of Philosophy

Chenghao Xiao

Ziqi Pan ziqi.pan2@durham.ac.uk
PGR Student Doctor of Philosophy

Abstract

Lacking behavioural data between students and an Intelligent Tutoring System (ITS) has been an obstacle for improving its personalisation capability. One feasible solution is to train “sim students”, who simulate real students’ behaviour in the ITS. We can then use their generated behavioural data to train the ITS to offer real students personalised learning strategies and trajectories. In this paper, we thus propose SimStu-Transformer, developed based on the Decision Transformer algorithm, to generate learning behavioural data.

Citation

Li, Z., Shi, L., Cristea, A., Zhou, Y., Xiao, C., & Pan, Z. (2022). SimStu-Transformer: A Transformer-Based Approach to Simulating Student Behaviour. In Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium (348-351). Springer, Cham. https://doi.org/10.1007/978-3-031-11647-6_67

Acceptance Date	Apr 25, 2022
Online Publication Date	Jul 26, 2022
Publication Date	2022
Deposit Date	Aug 31, 2022
Publicly Available Date	Jul 27, 2023
Pages	348-351
Series Title	Lecture Notes in Computer Science
Series Number	13356
Book Title	Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium
ISBN	978-3-031-11646-9
DOI	https://doi.org/10.1007/978-3-031-11647-6_67
Public URL	https://durham-repository.worktribe.com/output/1620863