Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks

Cognitive diagnosis is one of the essential components in intelligent education and aims to diagnose student’s skill or knowledge mastery based on their responses. Recently, with the development of artificial intelligence, some researchers have applied neural network methods to cognitive diagnosis....

Full description

Saved in:
Bibliographic Details
Main Authors: Jinhong Tao, Wei Zhao, Fengjuan Liu, Xiaoqing Guo, Nuo Cheng, Qian Guo, Xiaoqing Xu, Hong Duan
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154458966261760
author Jinhong Tao
Wei Zhao
Fengjuan Liu
Xiaoqing Guo
Nuo Cheng
Qian Guo
Xiaoqing Xu
Hong Duan
author_facet Jinhong Tao
Wei Zhao
Fengjuan Liu
Xiaoqing Guo
Nuo Cheng
Qian Guo
Xiaoqing Xu
Hong Duan
author_sort Jinhong Tao
collection DOAJ
description Cognitive diagnosis is one of the essential components in intelligent education and aims to diagnose student’s skill or knowledge mastery based on their responses. Recently, with the development of artificial intelligence, some researchers have applied neural network methods to cognitive diagnosis. Although they achieved some success, they seemed to lack a certain basis for designing network structures and could not obtain a unified method for designing network structures. We propose a neural network method for cognitive diagnosis based on Q-matrix constraints, introducing the Q-matrix from traditional cognitive diagnosis to enhance the reliability and interpretability of the network structure. Specifically, our method is highly consistent with generalized deterministic inputs, the noisy “and” gate model (GDINA), and the network structure reflects the direct contribution of skills to answering questions correctly, as well as the indirect contribution of interactions between skills to answering questions correctly. Finally, extensive experiments on both simulated and real datasets demonstrated that our method achieved high accuracy and reliability, with a particularly notable performance on low-quality datasets. As the number of questions and skills increased, our approach exhibited greater robustness compared to the classical methods, highlighting its potential for broad applicability in cognitive diagnosis tasks.
format Article
id doaj-art-5932a67799e740e597a8527e749c7c64
institution Kabale University
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-5932a67799e740e597a8527e749c7c642024-11-26T17:48:32ZengMDPI AGApplied Sciences2076-34172024-11-0114221038010.3390/app142210380Cognitive Diagnosis Method via Q-Matrix-Embedded Neural NetworksJinhong Tao0Wei Zhao1Fengjuan Liu2Xiaoqing Guo3Nuo Cheng4Qian Guo5Xiaoqing Xu6Hong Duan7School of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaSchool of Educational Science, Shaanxi University of Technology, 1 Dongyi, Hanzhong 723001, ChinaSchool of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaSchool of Information Science and Technology, Northeast Normal University, 2555 Jingyue, Changchun 130117, ChinaTeachers College, Shihezi University/Bingtuan Education Institute, 221 North 4th Road, Shihezi 832003, ChinaCognitive diagnosis is one of the essential components in intelligent education and aims to diagnose student’s skill or knowledge mastery based on their responses. Recently, with the development of artificial intelligence, some researchers have applied neural network methods to cognitive diagnosis. Although they achieved some success, they seemed to lack a certain basis for designing network structures and could not obtain a unified method for designing network structures. We propose a neural network method for cognitive diagnosis based on Q-matrix constraints, introducing the Q-matrix from traditional cognitive diagnosis to enhance the reliability and interpretability of the network structure. Specifically, our method is highly consistent with generalized deterministic inputs, the noisy “and” gate model (GDINA), and the network structure reflects the direct contribution of skills to answering questions correctly, as well as the indirect contribution of interactions between skills to answering questions correctly. Finally, extensive experiments on both simulated and real datasets demonstrated that our method achieved high accuracy and reliability, with a particularly notable performance on low-quality datasets. As the number of questions and skills increased, our approach exhibited greater robustness compared to the classical methods, highlighting its potential for broad applicability in cognitive diagnosis tasks.https://www.mdpi.com/2076-3417/14/22/10380cognitive diagnosis assessmentdiagnostic classification modelsQ-matrixmachine learningpsychometricscognitive tests
spellingShingle Jinhong Tao
Wei Zhao
Fengjuan Liu
Xiaoqing Guo
Nuo Cheng
Qian Guo
Xiaoqing Xu
Hong Duan
Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
Applied Sciences
cognitive diagnosis assessment
diagnostic classification models
Q-matrix
machine learning
psychometrics
cognitive tests
title Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
title_full Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
title_fullStr Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
title_full_unstemmed Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
title_short Cognitive Diagnosis Method via Q-Matrix-Embedded Neural Networks
title_sort cognitive diagnosis method via q matrix embedded neural networks
topic cognitive diagnosis assessment
diagnostic classification models
Q-matrix
machine learning
psychometrics
cognitive tests
url https://www.mdpi.com/2076-3417/14/22/10380
work_keys_str_mv AT jinhongtao cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT weizhao cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT fengjuanliu cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT xiaoqingguo cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT nuocheng cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT qianguo cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT xiaoqingxu cognitivediagnosismethodviaqmatrixembeddedneuralnetworks
AT hongduan cognitivediagnosismethodviaqmatrixembeddedneuralnetworks