Context based learning: a survey of contextual indicators for personalized and adaptive learning recommendations – a pedagogical and technical perspective

Abstract

Learning personalization has proven its effectiveness in enhancing learner performance. Therefore, modern digital learning platforms have been increasingly depending on recommendation systems to offer learners personalized suggestions of learning materials. Learners can utilize those recommendations to acquire certain skills for the labor market or for their formal education. Personalization can be based on several factors, such as personal preference, social connections or learning context. In an educational environment, the learning context plays an important role in generating sound recommendations, which not only fulfill the preferences of the learner, but also correspond to the pedagogical goals of the learning process. This is because a learning context describes the actual situation of the learner at the moment of requesting a learning recommendation. It provides information about the learner’s current state of knowledge, goal orientation, motivation, needs, available time, and other factors that reflect their status and may influence how learning recommendations are perceived and utilized. Context-aware recommender systems have the potential to reflect the logic that a learning expert may follow in recommending materials to students with respect to their status and needs. During the last decade, several approaches have emerged in the literature to define the learning context and the factors that may capture it. Those approaches led to different definitions of contextualized learner-profiles. In this paper, we review the state-of-the-art approaches for defining a user’s learning-context. We provide an overview of the definitions available, as well as the different factors that are considered when defining a context. Moreover, we further investigate the links between those factors and their pedagogical foundations in learning theories. We aim to provide a comprehensive understanding of contextualized learning from both pedagogical and technical points of view. By combining those two viewpoints, we aim to bridge a gap between both domains, in terms of contextualizing learning recommendations.

Problem-Based Learning-Path Recommendations Through Integrating Knowledge Graphs and Large Language Models

“…Learning path RS have been developed in recent years to offer learners a sequence of learning materials that can achieve a learning goal [1]. However, majority of RS use data about the learners themselves, e.g., in a user profile, to generate a personalized recommendation [1,2]. Analyzing real-life challenges that learners face and defining their learning goals are still difficult for automated recommendations.…”

Four Scenarios of Personalized Learning Integration Mediated by a Digital Platform

“…support this viewpoint, stating that ''technology is necessary to bring personalized learning to scale'' (p. 14), as well asAbu-Rasheed et al (2023) express the opinion that technology-enhanced learning has the potential to enable personalization. Contributing to digital technology implementation,Boninger et al (2019) argue that digital platforms are vital for a shift from a one-size-fits-all method to more personalized instructions.…”