Article: Enhancing skill prediction through generalising Bayesian knowledge tracing Journal: International Journal of Mobile Learning and Organisation (IJMLO) 2021 Vol.15 No.4 pp.358 - 373 Abstract: Learning Analytics (LA) have been widely investigated and applied to understand and optimise the learning process and environment. Among a number of LA tools, Bayesian Knowledge Tracing (BKT) was developed aiming at predicting the probability that a skill has been successfully acquired by a learner. While current development has proved BKT to be sufficiently accurate in prediction and useful, the state-of-the-art BKT methods suffer from a number of shortcomings such as the incapability to predict multiple skills learnt by a student. In this paper, we extend the ordinary BKT model to predict unlimited number of skills learned by a learner based on a non-parametric Dirichlet Process (DP). Another characteristic of our approach is that it can easily incorporate prior knowledge to our model resulting in a more accurate prediction. The extended model is more generic and able to handle border applications. We have developed two efficient approximate inference methods based on Gibbs sampling and variational methods. Inderscience Publishers - linking academia, business and industry through research

Title: Enhancing skill prediction through generalising Bayesian knowledge tracing

Authors: Tak-Lam Wong; Di Zou; Gary Cheng; Jeff Kai Tai Tang; Yi Cai; Fu Lee Wang

Addresses: Department of Computing Studies and Information Systems, Douglas College, British Columbia, Canada ' Department of English Language Education, The Education University of Hong Kong, Hong Kong SAR ' Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong SAR ' School of Science and Technology, Open University of Hong Kong, Hong Kong SAR ' School of Software Engineering, South China University of Technology, China ' School of Science and Technology, Open University of Hong Kong, Hong Kong SAR

Abstract: Learning Analytics (LA) have been widely investigated and applied to understand and optimise the learning process and environment. Among a number of LA tools, Bayesian Knowledge Tracing (BKT) was developed aiming at predicting the probability that a skill has been successfully acquired by a learner. While current development has proved BKT to be sufficiently accurate in prediction and useful, the state-of-the-art BKT methods suffer from a number of shortcomings such as the incapability to predict multiple skills learnt by a student. In this paper, we extend the ordinary BKT model to predict unlimited number of skills learned by a learner based on a non-parametric Dirichlet Process (DP). Another characteristic of our approach is that it can easily incorporate prior knowledge to our model resulting in a more accurate prediction. The extended model is more generic and able to handle border applications. We have developed two efficient approximate inference methods based on Gibbs sampling and variational methods.

Keywords: Bayesian knowledge tracing; BKT; learning analytics.

DOI: 10.1504/IJMLO.2021.118433

International Journal of Mobile Learning and Organisation, 2021 Vol.15 No.4, pp.358 - 373

Received: 04 Sep 2019
Accepted: 30 Dec 2019
Published online: 26 Oct 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Enhancing skill prediction through generalising Bayesian knowledge tracing

Keep up-to-date