Developing Explainable Artificial Intelligence to Enhance Transparency and Personalization in E-Learning Recommendation Systems

Abstract

The integration of Artificial Intelligence (AI) into educational frameworks has garnered increasing attention due to its potential to enhance learning experiences. However, the "black-box" nature of many AI-driven recommender systems raises concerns about transparency, interpretability, and user trust. This research focuses on utilizing Explainable AI (XAI) to improve both transparency and personalization in e-learning recommender systems. By leveraging XAI techniques, the study provides learners with clear explanations behind the recommendations of specific learning resources, fostering trust and deeper engagement. The proposed XAI-based e-learning recommender system combines machine learning algorithms with explainability models to personalize content while offering interpretable justifications. This approach enables learners to understand the rationale behind the recommendations, improving their decision-making and engagement. Empirical evaluations reveal that the system significantly enhances transparency without sacrificing accuracy or relevance. Additionally, personalized explanations boost learner satisfaction, motivation, and academic outcomes, emphasizing the need for explainability in ethical, user-centered educational technologies.