Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks
Online formative assessments in e-learning systems are increasingly of interest in the field of education. While substantial research into the model and item design aspects of formative assessment has been conducted, few software systems embodied with a psychometric model have been proposed to allow...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/22/8196 |
_version_ | 1797547453203873792 |
---|---|
author | Younyoung Choi Cayce McClenen |
author_facet | Younyoung Choi Cayce McClenen |
author_sort | Younyoung Choi |
collection | DOAJ |
description | Online formative assessments in e-learning systems are increasingly of interest in the field of education. While substantial research into the model and item design aspects of formative assessment has been conducted, few software systems embodied with a psychometric model have been proposed to allow us to adaptively implement formative assessments. This study aimed to develop an adaptive formative assessment system, called computerized formative adaptive testing (CAFT) by using artificial intelligence methods based on computerized adaptive testing (CAT) and Bayesian networks as learning analytics. CAFT can adaptively administer personalized formative assessment to a learner by dynamically selecting appropriate items and tests aligned with the learner’s ability. Forty items in an item bank were evaluated by 410 learners, moreover, 1000 learners were recruited for a simulation study and 120 learners were enrolled to evaluate the efficiency, validity, and reliability of CAFT in an application study. The results showed that, through CAFT, learners can adaptively take item s and tests in order to receive personalized diagnostic feedback about their learning progression. Consequently, this study highlights that a learning management system which integrates CAT as an artificially intelligent component is an efficient educational evaluation tool for a remote personalized learning service. |
first_indexed | 2024-03-10T14:44:21Z |
format | Article |
id | doaj.art-e5231b28b3684f54b95712058c941701 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T14:44:21Z |
publishDate | 2020-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e5231b28b3684f54b95712058c9417012023-11-20T21:32:10ZengMDPI AGApplied Sciences2076-34172020-11-011022819610.3390/app10228196Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian NetworksYounyoung Choi0Cayce McClenen1Department of Adolescent Coaching Counseling, Hanyang Cyber University, Seoul 04763, KoreaDepartment of Computer Science, McGill University, Montreal, QC H3A 1G1, CanadaOnline formative assessments in e-learning systems are increasingly of interest in the field of education. While substantial research into the model and item design aspects of formative assessment has been conducted, few software systems embodied with a psychometric model have been proposed to allow us to adaptively implement formative assessments. This study aimed to develop an adaptive formative assessment system, called computerized formative adaptive testing (CAFT) by using artificial intelligence methods based on computerized adaptive testing (CAT) and Bayesian networks as learning analytics. CAFT can adaptively administer personalized formative assessment to a learner by dynamically selecting appropriate items and tests aligned with the learner’s ability. Forty items in an item bank were evaluated by 410 learners, moreover, 1000 learners were recruited for a simulation study and 120 learners were enrolled to evaluate the efficiency, validity, and reliability of CAFT in an application study. The results showed that, through CAFT, learners can adaptively take item s and tests in order to receive personalized diagnostic feedback about their learning progression. Consequently, this study highlights that a learning management system which integrates CAT as an artificially intelligent component is an efficient educational evaluation tool for a remote personalized learning service.https://www.mdpi.com/2076-3417/10/22/8196computerized adaptive testingformative assessmentlearning management systemsartificial intelligence (AI) in educatione-learning technologieslearning analytics |
spellingShingle | Younyoung Choi Cayce McClenen Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks Applied Sciences computerized adaptive testing formative assessment learning management systems artificial intelligence (AI) in education e-learning technologies learning analytics |
title | Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks |
title_full | Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks |
title_fullStr | Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks |
title_full_unstemmed | Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks |
title_short | Development of Adaptive Formative Assessment System Using Computerized Adaptive Testing and Dynamic Bayesian Networks |
title_sort | development of adaptive formative assessment system using computerized adaptive testing and dynamic bayesian networks |
topic | computerized adaptive testing formative assessment learning management systems artificial intelligence (AI) in education e-learning technologies learning analytics |
url | https://www.mdpi.com/2076-3417/10/22/8196 |
work_keys_str_mv | AT younyoungchoi developmentofadaptiveformativeassessmentsystemusingcomputerizedadaptivetestinganddynamicbayesiannetworks AT caycemcclenen developmentofadaptiveformativeassessmentsystemusingcomputerizedadaptivetestinganddynamicbayesiannetworks |