A systematic literature review on adaptive content recommenders in personalized learning environments from 2015 to 2020

• Published in: Journal of computers in education (the official journal of the Global Chinese Society for Computers in Education) Vol. 9; no. 1; pp. 113 - 148
• Main Authors: Raj, Nisha S., Renumol, V. G.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2022; Springer Nature B.V
• Subjects: Algorithms; Artificial intelligence; Computers and Education; Course Content; Customization; Distance learning; Education; Educational Environment; Educational materials; Educational objectives; Educational Resources; Educational Technology; Electronic Learning; Filtration; Internet; Knowledge; Learning; Literature reviews; Machine learning; Online instruction; Ontology; Personalized learning; Recommender systems; School environment; Tags; Undergraduate Students; User satisfaction; Personalized learning environments; Machine learning algorithms; Recommeder systems; Learner model
• ISSN: 2197-9987; 2197-9995
• DOI: 10.1007/s40692-021-00199-4

In personalized learning, each student gets a customized learning plan according to their pace of learning, instructional preferences, learning objects, etc. Hence the content recommender system in Personalized Learning Environment (PLE) should adapt to learner attributes and suggest appropriate learning resources to aid the learning process and improve the learning outcomes. This systematic literature review aims to analyze and summarize the studies on learning content recommenders in adaptive and personalized learning environments from 2015 to 2020. The publications were searched using proper keywords and filtered using the inclusion and exclusion criteria, which resulted in 52 publications. This paper summarizes the recent trends in research on different aspects of the recommender systems, such as learner attributes, recommendation methods, evaluation metrics, and the usability tests used by the researchers. It is observed that cognitive aspects of learners like learning style, preferences, knowledge level, etc., are used by most studies than non-cognitive aspects as social tags or trust. In most cases, recommendation engines are a hybrid of collaborative filtering, content-based filtering, ontological approaches, etc. All models were evaluated for the correctness of the prediction done, and a few studies have also done evaluations based on learner satisfaction or usability.