A Method of Cognitive Diagnosis for Objective Problems Based on a Bayesian Network

DOI

10.2991/978-94-6463-574-4_13How to use a DOI?

Keywords

Bayesian network; cognitive diagnosis model; educational assessment; item response theory

Abstract

With the popularity of online education in recent years, intelligence tutoring systems (ITSs) have developed rapidly. One of the key technologies to embody ITS intelligence is its evaluation mechanism. However, the existing evaluation mechanism either stays at the ability level and cannot go deep into the analysis of students’ skills or can only conduct cognitive analysis and cannot give ability evaluation. To this end, an interpretable cognitive diagnosis model (CDM) based on a Bayesian network has been proposed for a particular kind of problem, an objective problem. Specifically, we first approximate the ability of examinees empirically, and then item response theory (IRT) is introduced to model the examinees’ proficiency in some skills. Finally, educational hypotheses and slip and guess factors were combined to infer the examinees’ scores on a problem. At the end of the paper, a specific example was presented to show the good interpretability of the model, and a cognitive diagnostic result can be easily derived. Experiments on real-world datasets prove that the CDM we proposed can reasonably estimate students’ ability level distribution, and the prediction task proves the effectiveness of CDM in-depth diagnosis.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Huanran Lin
AU  - Dongfeng Liu
PY  - 2024
DA  - 2024/11/21
TI  - A Method of Cognitive Diagnosis for Objective Problems Based on a Bayesian Network
BT  - Proceedings of the 4th International Conference on Internet, Education and Information Technology (IEIT 2024)
PB  - Atlantis Press
SP  - 109
EP  - 116
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6463-574-4_13
DO  - 10.2991/978-94-6463-574-4_13
ID  - Lin2024
ER  -