A COMPREHENSIVE BIBLIOGRAPHIC ANALYSIS OF COURSE RECOMMENDATION SYSTEMS FOR UNIVERSITY STUDENTS

Objectives: The objective of the current study is to highlight the recent focus that has shifted towards developing course recommendation systems for university students, leveraging deep learning techniques to sift through vast amounts of data and provide personalized recommendations. Methods: Deep learning has proven advantageous, addressing issues like accuracy, sparsity, and scalability encountered in traditional methods. By considering factors such as student preferences, course attributes, career prospects, and feedback, these systems aim to guide students towards achieving their academic objectives. This article delves into the bibliometric aspects of university course recommendation systems, drawing from Scopus’s extensive database to analyze scholarly contributions over past 22 years. Findings: By examining publication timelines, geographical distributions, and disciplinary trends, this analysis maps the intellectual landscape of the field. Additionally, co-authorship and keyword co-occurrence analyses conducted using VOSviewer software offer insights into collaborative networks and emerging themes within the research domain. This comprehensive examination sheds light on key advancements, influential contributors, and burgeoning areas within course recommendation systems. Novelty: There is a focus on deep learning approaches and obvouslay this study is a holistic approach that provides a fresh prospective on the evolution and future prospectives of the course recommendation systems by performing comprehensive analysis of past 22 years of available data from scopus.