Recommendation Algorithms for Educational Systems

2026

Closed access Metadata (CSL-JSON)
DOI 10.14445/22315381/ijett-v74i4p120
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

This study offers an in-depth review of techniques and tools used in supporting personalized learning in e-learning environments. The techniques and tools discussed in this study include user-centric and technology-centric techniques, such as several popular models of learning styles, including the Myers-Briggs Type Indicator, Kolb’s theory of experiential learning, Dunn and Dunn’s learning style model, and Felder-Silverman’s learning style model. The technological aspects discussed in this study include an overview of the Protus system, which is used as an example of how adaptive hypermedia and semantic technologies can be used in supporting personalized learning. The combination of user modeling and recent advances in technology highlights the limitations of both techniques when used in isolation. The limitations discussed in this study include ethical concerns, data privacy, and the lack of standardization in recommendations. The analysis ends with an overview of future research possibilities, such as using natural language processing in combination with adaptive personalization techniques.