Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chakravarty, Abhirup, Brenchley, Mark, Breakspear, Trevor, Lewin, Ian, Huang, Yan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912758883155968
author Chakravarty, Abhirup
Brenchley, Mark
Breakspear, Trevor
Lewin, Ian
Huang, Yan
author_facet Chakravarty, Abhirup
Brenchley, Mark
Breakspear, Trevor
Lewin, Ian
Huang, Yan
contents A key ethical challenge in Automated Essay Scoring (AES) is ensuring that scores are only released when they meet high reliability standards. Confidence modelling addresses this by assigning a reliability estimate measure, in the form of a confidence score, to each automated score. In this study, we frame confidence estimation as a classification task: predicting whether an AES-generated score correctly places a candidate in the appropriate CEFR level. While this is a binary decision, we leverage the inherent granularity of the scoring domain in two ways. First, we reformulate the task as an n-ary classification problem using score binning. Second, we introduce a set of novel Kernel Weighted Ordinal Categorical Cross Entropy (KWOCCE) loss functions that incorporate the ordinal structure of CEFR labels. Our best-performing model achieves an F1 score of 0.97, and enables the system to release 47% of scores with 100% CEFR agreement and 99% with at least 95% CEFR agreement -compared to approximately 92% (approx.) CEFR agreement from the standalone AES model where we release all AM predicted scores.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23315
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments
Chakravarty, Abhirup
Brenchley, Mark
Breakspear, Trevor
Lewin, Ian
Huang, Yan
Computation and Language
Artificial Intelligence
Machine Learning
A key ethical challenge in Automated Essay Scoring (AES) is ensuring that scores are only released when they meet high reliability standards. Confidence modelling addresses this by assigning a reliability estimate measure, in the form of a confidence score, to each automated score. In this study, we frame confidence estimation as a classification task: predicting whether an AES-generated score correctly places a candidate in the appropriate CEFR level. While this is a binary decision, we leverage the inherent granularity of the scoring domain in two ways. First, we reformulate the task as an n-ary classification problem using score binning. Second, we introduce a set of novel Kernel Weighted Ordinal Categorical Cross Entropy (KWOCCE) loss functions that incorporate the ordinal structure of CEFR labels. Our best-performing model achieves an F1 score of 0.97, and enables the system to release 47% of scores with 100% CEFR agreement and 99% with at least 95% CEFR agreement -compared to approximately 92% (approx.) CEFR agreement from the standalone AES model where we release all AM predicted scores.
title Enhancing Marker Scoring Accuracy through Ordinal Confidence Modelling in Educational Assessments
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.23315