The Development of MCQ generating system based on Ontology Concepts

Abstract

Education system needs an effective method to evaluate students in a competent way on their major concepts learned from their studies. Generating Multiple Choice Questions (MCQ) process is cumbersome and needs a lot of effort especially among novice instructors. The current MCQ generators do not automatically generate questions but only randomly display questions from the question bank. However, it is not easy to load a massive number of questions in the question banks where it is normally done in stages to have massive question collection in the question bank. Therefore, this paper proposes an automatic question generator specifically for MCQ to enable a massive number of questions generated in just a few seconds. In addition, it is useful for students who have to do self-learning for their tutorial exercises especially during the COVID-19 pandemic crisis where online learning is widely used to replace the traditional face-to-face sessions. The generator has adopted an ontological approach for question generation strategies, and it is implemented using rule-based reasoning. There are six modules proposed and discussed in this paper including the concept extraction from ontology, concept, and question stem mapping, generating appropriate answer options using ontology relation information and reordering of answer options. The functionality and validation test showed that Multiple Choice Question Generator (MCQ-G) can generate MCQ with appropriate answer options. This work will be extended in the future using the difference domain ontology and question types.