RECOMMENDATION MODELS FOR MENTORSHIP MATCHING: A COMPARATIVE STUDY OF PARTICLE SWARM OPTIMIZATION AND CUCKOO SEARCH ALGORITHMS

Abstract

Effective mentorship is vital for personal and professional growth, particularly in academic and professional settings. However, finding the right mentor from a large number of academic researchers available today can be a challenging task, particularly for newcomers to the field or for research institutions seeking to facilitate mentorship matches. Scholarly recommender systems (SRSs) have been identified as efficient tools in academic and research settings, but they also pose a significant challenge due to their high-dimensional search spaces, a challenge that metaheuristic algorithms have emerged to tackle with efficiency. This approach leverages profile and publication data from the Academic Family Tree (AFT) database and employs Particle Swarm Optimization (PSO) and Cuckoo Search (CS) algorithms to optimize mentorship matching. Data mining methodology consisting of data acquisition, pre-processing, training, and testing was used in this study. Experimental results revealed superior performance, with PSO achieving precision, recall, and accuracy of 1.00, alongside a mean reciprocal rank (MRR) of 0.80. Notably, PSO outperformed CS, which yielded a precision of 0.94, recall of 0.83, accuracy of 0.90, and an MRR of 0.80 at 10 recommendations. These findings underscore the potential of PSO in developing reliable mentorship matching systems.