Ontology-based information extraction for subject-focussed automatic essay evaluation

Automatic essay evaluation (AEE) systems are designed to assist a teacher in the task of classroom assessment in order to alleviate the demands of manual subject evaluation. However, although numerous AEE systems are available, most of these systems do not use elaborate domain knowledge for evaluation, which limits their ability to give informative feedback to students and also their ability to constructively grade a student based on a particular domain of study. This paper is aimed at improving on the achievements of previous studies by providing a subject-focussed evaluation system that considers the domain knowledge while scoring and provides informative feedback to its user. The study employs a combination of techniques such as system design and modelling using Unified Modelling Language (UML), information extraction, ontology development, data management, and semantic matching in order to develop a prototype subject-focussed AEE system. The developed system was evaluated to determine its level of performance and usability. The result of the usability evaluation showed that the system has an overall mean rating of 4.17 out of maximum of 5, which indicates `good usability'. In terms of performance, the assessment done by the system was also found to have sufficiently high correlation with those done by domain experts, in addition to providing appropriate feedback to the user.