Quantifying the Impact of AI-Driven Content Personalization on Learning Outcomes and User Engagement

The rapid expansion of digital education has significantly transformed knowledge delivery. However, ensuring equitable accessibility for diverse learners remains a persistent challenge, particularly for individuals with varying cognitive abilities, technological resources, and learning preferences. This study aims to develop and evaluate an adaptive AI-driven e-learning platform designed to enhance accessibility and improve learning outcomes across heterogeneous learner populations. The proposed system integrates machine learning–based personalization and inclusive design principles to dynamically adjust content delivery, learning paths, and interface features according to individual user profiles. A mixed-method approach was employed, combining quantitative surveys and qualitative interviews with learners, educators, and technology experts, alongside prototype development and experimental evaluation. The results indicate that the adaptive platform improved accessibility satisfaction by 25\%, increased average learning performance by 25\%, and enhanced user engagement by 20\%, demonstrating its effectiveness in reducing learning barriers and supporting personalized education. These findings highlight the critical role of AI-driven adaptation in fostering inclusive and efficient digital learning environments. The study concludes that integrating intelligent personalization with accessibility-focused design can significantly contribute to achieving educational equity in technologically diverse contexts. Nevertheless, the research is limited by sample size and short-term evaluation, indicating a gap in long-term performance assessment and scalability across broader educational settings. Future work should focus on integrating advanced predictive analytics, expanding real-world deployment, and evaluating longitudinal impacts to further validate and optimize adaptive e-learning systems.