A Rule-Based Expert System for Academic Advising and Guidance Toward Undergraduate Students

Abstract

The provision of academic guidance to undergraduate students is a crucial and significant duty for the academic faculty in most prestigious universities. Expert systems are often regarded as one of the most successful areas in the field of artificial intelligence. The system utilizes a rule-based decision engine to assist individuals lacking experience in enhancing their skills. Nevertheless, a significant number of students are required to meet with their advisors to arrange their study schedule. This thesis is driven by the belief that the successful development of an academic advisory expert system will result in an expansion of the range and extent of challenges that students, academic staff, and other academic activities can effectively address, leading to a higher level of achievement in the university learning process. Nevertheless, the effectiveness of an advisory expert system is constrained by the caliber of the acquired knowledge, specifically in the context of academic advisory expert systems. The performance of such systems is primarily determined by the quality of the framework employed for academic expert knowledge acquisition. The objective of this study is to suggest a revision of the current knowledge acquisition framework in order to make it appropriate for implementation in higher education institutions. The proposed modification aims to create a prototype rule-based expert system specifically designed for academic advising of undergraduate students. The system's output also offers a precise and conflict-free course proposal for the undergraduate student. It functions as a mentor, providing undergraduate students with guidance and recommendations for suitable subjects based on their completed courses, prerequisites, and project scope, as defined by the student themselves. According to the empirical findings, the utilization of the proposed model for an undergraduate advisory expert system resulted in a noteworthy enhancement in performance.