Educational recommender systems: a bibliometric analysis for the period 2002 – 2022

• Main Authors: Noratiqah Mohd Ariff, Lee, Bernard Kok Bang, Sarmela Nadarajan, Muhammed Haziq Muhammed Nor
• Format: Article
• Language: English
• Published: Penerbit Universiti Kebangsaan Malaysia 2024
• Online Access: http://journalarticle.ukm.my/24113/1/197_215%20Paper_14.pdf; http://journalarticle.ukm.my/24113/; http://www.ukm.my/jqma
• Institution: Universiti Kebangsaan Malaysia

Recommender systems have been applied across various domains to address the challenge of information overload by furnishing users with a personalised and pertinent recommendations. The surge in educational resources, notably within the e-learning content realm, has spurred educational recommender systems’ emergence. Numerous studies have delved into these systems, employing diverse approaches and techniques to enhance the accuracy of recommendations. Consequently, analysing scholarly work on educational recommender systems becomes pivotal, providing an overview of prevalent trends and explored subjects within the field. This study aims to gather statistical information on educational recommender systems by conducting a bibliometric analysis of related papers published in the Web of Science (WoS) database from 2002 to 2022. The analysis includes examining the annual publication trend, the leading authors, journals, and countries, the most impactful articles, and the collaborative networks among countries. Then, the most common keywords, keyword clusters, and relationships between keywords were analysed with a word cloud and keyword cooccurrence network. This study also uncovers the important themes in education recommender systems research over time. The findings indicate that the main technique used in educational recommender systems is the collaborative filtering technique. However, in recent years, content based filtering has also been applied with an inclination for natural language processing techniques. Overall, this paper presents broad insights into studies on educational recommender systems to allow the discovery of potential future topics in the domain.