Abstract:
Teachers aim to transmit their knowledge to students so that they acquire certain accepted and shared concepts. However, what students actually understand is, in many cases, something completely different. Students build their own conceptual models as a network of interrelated concepts depending on their particular background and emotions. In fact, according to the Ausubel’s Learning Theory, students will only be able to learn new concepts provided that they have the previous necessary concepts to which the new ones have to be linked to. Intelligent Tutoring Systems (ITSs) are educational software containing some kind of intelligent component to imitate how a human teacher would behave when teaching. Adaptive Educational Hypermedia Systems (AEHSS) are inspired in ITSs to adapt the content and navigation in the course to each student’s model. The assessment of these systems is usually focused on the so-called objective testing (Multiple-Choice Questions, fill-in-the-blank items, etc.). The objective testing fails to identify many students’ deep underlying misconceptions. Hence, automatic assessment of free-text answers is a field that has attracted much attention in the last decades.
This research work presents the development of an Expert System (ES) capable of acquiring the knowledge from Subject Matter Experts (SMEs) in a specific field of Computer Science. The system uses a built-in Inference Engine designed with Shallow Natural Language Processing Techniques (Information Extraction using Tokenization, Statistical Keyword Analysis and Domain-Specific Dictionary) and a Fuzzy-Scoring Model to assess Students’ Free-Text Answers to Open-Ended Questions. The correctness of students’ answers is computed with respect to lecturers’ underlying model answers or templates. The newly developed ES was adapted to Software Engineering in Federal University of Technology Akure (FUTA) and its performance was evaluated using Statistical Metrics. The results show the effectiveness and the accuracy of the proposed system in Open-Ended examination processing. The comparative analysis of the obtained results with the results obtained from some existing Automated Essay Scoring Systems also show a good performance of the system.
