Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education

Machine learning (ML) application to grading has been gaining traction in educational system given arguments that it has the potential to effectively analyse and evaluate diverse responses typical of open-ended examination, thereby enhancing assessment and feedback processes. By comparing confidenc...

Full description

Saved in:
Bibliographic Details
Main Author: Husain
Format: Article
Language:English
Published: Universitas Pendidikan Ganesha 2025-04-01
Series:Journal of Education Technology
Subjects:
Online Access:https://ejournal.undiksha.ac.id/index.php/JET/article/view/92673
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713011722289152
author Husain
author_facet Husain
author_sort Husain
collection DOAJ
description Machine learning (ML) application to grading has been gaining traction in educational system given arguments that it has the potential to effectively analyse and evaluate diverse responses typical of open-ended examination, thereby enhancing assessment and feedback processes. By comparing confidence index to experience, the study examined ML grading of open-ended examinations within the accounting education, with an aim to eliminate the black-box effect. Based on a probit modelling, confidence index significantly and positively impacts grading while experience showed mixed effects. Our findings suggest the integration of confidence indices would enhance transparency and interpretability, thereby eliminating black-box effect. The study provides critical steps for transparent ML grading to balance subjective and objective metrics, while ensuring fairness and reliability in academic and professional assessments
format Article
id doaj-art-1813ea0f1de24d0a91c0ffebf09bb34c
institution DOAJ
issn 2549-4856
2549-8290
language English
publishDate 2025-04-01
publisher Universitas Pendidikan Ganesha
record_format Article
series Journal of Education Technology
spelling doaj-art-1813ea0f1de24d0a91c0ffebf09bb34c2025-08-20T03:14:06ZengUniversitas Pendidikan GaneshaJournal of Education Technology2549-48562549-82902025-04-0191Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting EducationHusain0University of Johannesburg Machine learning (ML) application to grading has been gaining traction in educational system given arguments that it has the potential to effectively analyse and evaluate diverse responses typical of open-ended examination, thereby enhancing assessment and feedback processes. By comparing confidence index to experience, the study examined ML grading of open-ended examinations within the accounting education, with an aim to eliminate the black-box effect. Based on a probit modelling, confidence index significantly and positively impacts grading while experience showed mixed effects. Our findings suggest the integration of confidence indices would enhance transparency and interpretability, thereby eliminating black-box effect. The study provides critical steps for transparent ML grading to balance subjective and objective metrics, while ensuring fairness and reliability in academic and professional assessments https://ejournal.undiksha.ac.id/index.php/JET/article/view/92673Artificial Intelligence, Students with Disabilities, Learning Outcomes, Educational Assessment, Machine Learning, Inclusive Education.Education in Industrial Revolution 4.0
spellingShingle Husain
Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
Journal of Education Technology
Artificial Intelligence, Students with Disabilities, Learning Outcomes, Educational Assessment, Machine Learning, Inclusive Education.
Education in Industrial Revolution 4.0
title Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
title_full Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
title_fullStr Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
title_full_unstemmed Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
title_short Addressing the Black-Box Challenge: Confidence Index Approach to Grading of Open-Ended Assessments in Accounting Education
title_sort addressing the black box challenge confidence index approach to grading of open ended assessments in accounting education
topic Artificial Intelligence, Students with Disabilities, Learning Outcomes, Educational Assessment, Machine Learning, Inclusive Education.
Education in Industrial Revolution 4.0
url https://ejournal.undiksha.ac.id/index.php/JET/article/view/92673
work_keys_str_mv AT husain addressingtheblackboxchallengeconfidenceindexapproachtogradingofopenendedassessmentsinaccountingeducation