An evolutionary-based educational expert system to maximize student-supervisor compatibility

Web rapid development has provided new learning environments, bringing online education as a necessity in many sectors of the society. In such an environment, selecting supervisor is a critical decision that graduate students as well as professors are involved with, which could benefit from e-learning tools. In this paper we have proposed a solution for student-supervisor assignment based on Genetic Algorithm (GA), so that the task of student-supervisor assignment is mapped to an optimization problem that could be solved with GA approaches. In our GA approach, search space is the set of all bipartite graphs that are transformed to arrays of integer numbers as chromosomes representations. Assigning supervisors to students requires some information about professors and students. For this purpose, we have profiled students and professors through deriving their decision parameters and other required information, using data obtained from various sources including Learning Management System (LMS), Community of Practice (CoP), as well as our question-answering user interface. This system is implemented at the University of Tehran, using different profiles of students and professors. Delivery results suggest that our new method provides good precision in student-supervisor compatibility.