Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering

Constructed response items that require the student to give more detailed and elaborate responses are widely applied in large-scale assessments. However, the hand-craft scoring with a rubric for massive responses is labor-intensive and impractical due to rater subjectivity and answer variability. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingjing Luo, Hang Yang, Zhiwu Li, Witold Pedrycz
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Systems
Subjects:
Online Access:https://www.mdpi.com/2079-8954/12/9/380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850259385358483456
author Lingjing Luo
Hang Yang
Zhiwu Li
Witold Pedrycz
author_facet Lingjing Luo
Hang Yang
Zhiwu Li
Witold Pedrycz
author_sort Lingjing Luo
collection DOAJ
description Constructed response items that require the student to give more detailed and elaborate responses are widely applied in large-scale assessments. However, the hand-craft scoring with a rubric for massive responses is labor-intensive and impractical due to rater subjectivity and answer variability. The automatic response coding method, such as the automatic scoring of short answers, has become a critical component of the learning and assessment system. In this paper, we propose an interactive coding system called ASSIST to efficiently score student responses with expert knowledge and then generate an automatic score classifier. First, the ungraded responses are clustered to generate specific codes, representative responses, and indicator words. The constraint set based on feedback from experts is taken as training data in metric learning to compensate for machine bias. Meanwhile, the classifier from responses to code is trained according to the clustering results. Second, the experts review each coded cluster with the representative responses and indicator words to score a rating. The coded cluster and score pairs will be validated to ensure inter-rater reliability. Finally, the classifier is available for scoring a new response with out-of-distribution detection, which is based on the similarity between response representation and class proxy, i.e., the weight of class in the last linear layer of the classifier. The originality of the system developed stems from the interactive response clustering procedure, which involves expert feedback and an adaptive automatic classifier that can identify new response classes. The proposed system is evaluated on our real-world assessment dataset. The results of the experiments demonstrate the effectiveness of the proposed system in saving human effort and improving scoring performance. The average improvements in clustering quality and scoring accuracy are 14.48% and 18.94%, respectively. Additionally, we reported the inter-rater reliability, out-of-distribution rate, and cluster statistics, before and after interaction.
format Article
id doaj-art-ddcf791fdac04782b7ab206bafd3ae2e
institution OA Journals
issn 2079-8954
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Systems
spelling doaj-art-ddcf791fdac04782b7ab206bafd3ae2e2025-08-20T01:55:52ZengMDPI AGSystems2079-89542024-09-0112938010.3390/systems12090380Learning to Score: A Coding System for Constructed Response Items via Interactive ClusteringLingjing Luo0Hang Yang1Zhiwu Li2Witold Pedrycz3School of Marxism, University of Electronic Science and Technology of China, Chengdu 611731, ChinaMacau Institute of Systems Engineering, Macau University of Science and Technology, Macau, ChinaMacau Institute of Systems Engineering, Macau University of Science and Technology, Macau, ChinaDepartment of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6R 2V4, CanadaConstructed response items that require the student to give more detailed and elaborate responses are widely applied in large-scale assessments. However, the hand-craft scoring with a rubric for massive responses is labor-intensive and impractical due to rater subjectivity and answer variability. The automatic response coding method, such as the automatic scoring of short answers, has become a critical component of the learning and assessment system. In this paper, we propose an interactive coding system called ASSIST to efficiently score student responses with expert knowledge and then generate an automatic score classifier. First, the ungraded responses are clustered to generate specific codes, representative responses, and indicator words. The constraint set based on feedback from experts is taken as training data in metric learning to compensate for machine bias. Meanwhile, the classifier from responses to code is trained according to the clustering results. Second, the experts review each coded cluster with the representative responses and indicator words to score a rating. The coded cluster and score pairs will be validated to ensure inter-rater reliability. Finally, the classifier is available for scoring a new response with out-of-distribution detection, which is based on the similarity between response representation and class proxy, i.e., the weight of class in the last linear layer of the classifier. The originality of the system developed stems from the interactive response clustering procedure, which involves expert feedback and an adaptive automatic classifier that can identify new response classes. The proposed system is evaluated on our real-world assessment dataset. The results of the experiments demonstrate the effectiveness of the proposed system in saving human effort and improving scoring performance. The average improvements in clustering quality and scoring accuracy are 14.48% and 18.94%, respectively. Additionally, we reported the inter-rater reliability, out-of-distribution rate, and cluster statistics, before and after interaction.https://www.mdpi.com/2079-8954/12/9/380constructed response itemsresponse codingtext clusteringlarge-scale assessment
spellingShingle Lingjing Luo
Hang Yang
Zhiwu Li
Witold Pedrycz
Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
Systems
constructed response items
response coding
text clustering
large-scale assessment
title Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
title_full Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
title_fullStr Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
title_full_unstemmed Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
title_short Learning to Score: A Coding System for Constructed Response Items via Interactive Clustering
title_sort learning to score a coding system for constructed response items via interactive clustering
topic constructed response items
response coding
text clustering
large-scale assessment
url https://www.mdpi.com/2079-8954/12/9/380
work_keys_str_mv AT lingjingluo learningtoscoreacodingsystemforconstructedresponseitemsviainteractiveclustering
AT hangyang learningtoscoreacodingsystemforconstructedresponseitemsviainteractiveclustering
AT zhiwuli learningtoscoreacodingsystemforconstructedresponseitemsviainteractiveclustering
AT witoldpedrycz learningtoscoreacodingsystemforconstructedresponseitemsviainteractiveclustering