Ablation study on feature group importance for automated essay scoring

Grading of written academic essays by humans requires significant effort. It is a time-consuming task and is vulnerable to human biases. Ever since the introduction of modern computing, this has been one of the many automations being explored. Researches in automated essay scoring have been on-going...

Full description

Bibliographic Details
Main Authors: Tan, Jih Soong, Tan, Ian K.T.
Format: Article
Language:English
Published: Penerbit Universiti Kebangsaan Malaysia 2022
Online Access:http://journalarticle.ukm.my/19430/
http://journalarticle.ukm.my/19430/1/08.pdf
_version_ 1848814839026155520
author Tan, Jih Soong
Tan, Ian K.T.
author_facet Tan, Jih Soong
Tan, Ian K.T.
author_sort Tan, Jih Soong
building UKM Institutional Repository
collection Online Access
description Grading of written academic essays by humans requires significant effort. It is a time-consuming task and is vulnerable to human biases. Ever since the introduction of modern computing, this has been one of the many automations being explored. Researches in automated essay scoring have been on-going, where the majority of the researches in recent years are based on extracting multiple linguistic features and using them to build a classification model for automated essay scoring. The 3 main types of features used are lexical, grammatical, and semantic. In our work, we conducted an ablation study to discover the engineered features that has the weakest influence. We did this using a generic feature engineering and classification approach that was used by the winners of the Automated Student Assessment Prize (ASAP). This is to mitigate biases that may have addressed specific feature engineering or models. Our results show that a semantic feature called the prompt has been the weakest feature in influencing the models. From further investigations, this was due to it being over-fitted in the classification model.
first_indexed 2025-11-15T00:40:27Z
format Article
id oai:generic.eprints.org:19430
institution Universiti Kebangasaan Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T00:40:27Z
publishDate 2022
publisher Penerbit Universiti Kebangsaan Malaysia
recordtype eprints
repository_type Digital Repository
spelling oai:generic.eprints.org:194302022-08-18T08:21:37Z http://journalarticle.ukm.my/19430/ Ablation study on feature group importance for automated essay scoring Tan, Jih Soong Tan, Ian K.T. Grading of written academic essays by humans requires significant effort. It is a time-consuming task and is vulnerable to human biases. Ever since the introduction of modern computing, this has been one of the many automations being explored. Researches in automated essay scoring have been on-going, where the majority of the researches in recent years are based on extracting multiple linguistic features and using them to build a classification model for automated essay scoring. The 3 main types of features used are lexical, grammatical, and semantic. In our work, we conducted an ablation study to discover the engineered features that has the weakest influence. We did this using a generic feature engineering and classification approach that was used by the winners of the Automated Student Assessment Prize (ASAP). This is to mitigate biases that may have addressed specific feature engineering or models. Our results show that a semantic feature called the prompt has been the weakest feature in influencing the models. From further investigations, this was due to it being over-fitted in the classification model. Penerbit Universiti Kebangsaan Malaysia 2022-06 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/19430/1/08.pdf Tan, Jih Soong and Tan, Ian K.T. (2022) Ablation study on feature group importance for automated essay scoring. Asia-Pacific Journal of Information Technology and Multimedia, 11 (1). pp. 90-101. ISSN 2289-2192 https://www.ukm.my/apjitm/articles-issues
spellingShingle Tan, Jih Soong
Tan, Ian K.T.
Ablation study on feature group importance for automated essay scoring
title Ablation study on feature group importance for automated essay scoring
title_full Ablation study on feature group importance for automated essay scoring
title_fullStr Ablation study on feature group importance for automated essay scoring
title_full_unstemmed Ablation study on feature group importance for automated essay scoring
title_short Ablation study on feature group importance for automated essay scoring
title_sort ablation study on feature group importance for automated essay scoring
url http://journalarticle.ukm.my/19430/
http://journalarticle.ukm.my/19430/
http://journalarticle.ukm.my/19430/1/08.pdf