Enhancing context-aware personalized learning: A comparative study of traditional and emotion-aware ML algorithms

Abstract

In the evolving landscape of personalized learning (PL), the integration of contextual and emotional awareness is crucial to address learner-specific needs. This paper presents a comparative study analysing the performance and relevance of traditional personalized learning models versus context-aware personalized learning (CAPL) systems. The study reviews and synthesizes 15 peer-reviewed research articles published between 2018 and 2024, highlighting diverse approaches including emotion detection using VADER and machine learning classifiers like MLP, SVM, and Random Forest. A key insight from this comparison reveals that emotion-aware and context-sensitive models significantly enhance learner engagement and content adaptability, especially in dynamic learning environments. This study emphasizes the potential of CAPL systems to bridge the limitations of traditional PL and pave the way for smarter educational systems.