An Automated English Essay Scoring Engine Based on Neutrosophic Ontology for Electronic Education Systems

Abstract

Most educators agree that essays are the best way to evaluate students’ understanding, guide their studies, and track their growth as learners. Manually grading student essays is a tedious but necessary part of the learning process. Automated Essay Scoring (AES) provides a feasible approach to completing this process. Interest in this area of study has exploded in recent years owing to the difficulty of simultaneously improving the syntactic and semantic scores of an article. Ontology enables us to consider the semantic constraints of the actual world. However, there are several uncertainties and ambiguities that cannot be accounted for by standard ontologies. Numerous AES strategies based on fuzzy ontologies have been proposed in recent years to reduce the possibility of imprecise knowledge presentation. However, no known efforts have been made to utilize ontologies with a higher level of fuzzification in order to enhance the effectiveness of identifying semantic mistakes. This paper presents the first attempt to address this problem by developing a model for efficient grading of English essays using latent semantic analysis (LSA) and neutrosophic ontology. In this regard, the presented work integrates commonly used syntactic and semantic features to score the essay. The integration methodology is implemented through feature-level fusion. This integrated vector is used to check the coherence and cohesion of the essay. Furthermore, the role of neutrosophic ontology is investigated by adding neutrosophic membership functions to the crisp ontology to detect semantic errors and give feedback. Neutrosophic logic allows the explicit inclusion of degrees of truthfulness, falsity, and indeterminacy. According to the comparison with state-of-the-art AES methods, the results show that the proposed model significantly improves the accuracy of scoring the essay semantically and syntactically and is able to provide feedback.