An intelligent expert system for academic advising utilizing fuzzy logic and semantic web technologies for smart cities education

• Published in: Journal of computers in education (the official journal of the Global Chinese Society for Computers in Education) 2023-06, Vol.10 (2), p.293-323
• Main Authors: Iatrellis, Omiros, Stamatiadis, Evangelos, Samaras, Nicholas, Panagiotakopoulos, Theodor, Fitsilis, Panos
• Format: Article
• Language: English
• Subjects: Academic Advising; Academic guidance counseling; Case studies; Classification; Cognitive Style; Computers and Education; Customization; Decision making; Education; Educational Technology; Expert systems; Fuzzy logic; Higher education institutions; Integrated software; Knowledge; Learning; Learning Processes; Literature reviews; Multivalued logic; Online instruction; Personalized learning; Recommender systems; Registration; Semantic web; Semantics; Software; Students
• ISSN: 2197-9987; 2197-9995
• DOI: 10.1007/s40692-022-00232-0

Students attending Higher Education Institutions (HEIs) are faced with a variety of complex decisions and procedures. To provide students with more sustained and personalized advising, many HEIs turn to online academic advising systems and tools as a way to minimize costs and streamline their advising services. However, in such systems, uncertainty in the learner’s parameters is a factor, which makes the decision-making process more difficult. Fuzzy logic, a multivalued logic similar to human thinking and interpretation, is highly suitable and applicable for developing knowledge-based academic advising systems that conserve the inherent fuzziness in learner models. In this paper, an innovative hybrid software infrastructure is presented which integrates expert system, fuzzy reasoning, and ontological tools to provide reliable recommendations to students for the next appropriate learning step. The software comprises a fuzzy logic component that determines the student’s interest degree for a specific academic choice accompanied by an ontological model and a conventional rule-based expert system for the composition of personalized learning pathways. In order for the system to recommend the next step of the learning pathway, the output of the fuzzy logic component together with the knowledge that is modeled as part of the multi-facet ontology and the machine perceptible academic advising guidelines expressed as semantic rules interoperate in a dynamic and seamless manner. The paper presents the key modeling artifacts of the proposed approach and the architecture of the implemented prototype system. During the case study, the developed system yielded satisfactory results in terms of overall inter-rater reliability and usefulness.