Ablation study on feature group importance for automated essay scoring

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


Official URL: https://www.ukm.my/apjitm/articles-issues


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.

Item Type:Article
Keywords:Automated essay scorin; Ablation study; Feature engineering; Semantic; ASAP
Journal:Asia - Pasific Journal of Information Technology and Multimedia (Formerly Jurnal Teknologi Maklumat dan Multimedia)
ID Code:19430
Deposited By: ms aida -
Deposited On:16 Aug 2022 03:02
Last Modified:18 Aug 2022 08:21

Repository Staff Only: item control page