Personalization of Learning through Artificial Intelligence: An Analysis of Adaptive Models in Digital Education

Abstract

This article presents a systematic analysis of the scientific literature on the personalization of learning through artificial intelligence (AI), focusing on the adaptive models applied to digital education during the period 2023-2024. Through a review of articles indexed in Scopus and WoS, the most recent advances in the use of AI to create more personalized and efficient learning environments are explored, dynamically adjusting content, pacing, and pedagogical strategies according to the individual needs of students. The results suggest that the integration of AI-based adaptive models can significantly improve students' academic performance, motivation, and engagement. However, challenges are also identified, such as teacher resistance, lack of adequate infrastructure, and concerns about data privacy and equity in access to technology. This article concludes that while personalization of learning using AI offers great potential to transform education, its successful implementation requires overcoming technological and ethical barriers, as well as ongoing training for educators. In addition, it is suggested that future research should focus on evaluating the long-term effects of these adaptive models on students' well-being and educational outcomes.