Machine learning for the improvement of adaptive learning in university education

Abstract

AI is increasingly being introduced in the field of education and the educational system, with this the approach to the personalization of education according to the needs of each student. This review aims to analyze the impact of adaptive learning with artificial intelligence and machine learning techniques in improving learning in university education by identifying the main applications, benefits and challenges of this technology. The Scopus database was extensively searched, where 22 of 125 studies found met the inclusion criteria. The results showed that the classification of students according to their type of perception of educational content and the use of written text analysis as a basis for this classification were proposed as strategies to improve the quality and personalization of education. Likewise, the usefulness of machine learning algorithms based on SVM to predict students' final grades and detect possible learning difficulties was highlighted. It was concluded that early detection of learning difficulties, personalization of learning and consideration of demographic and gender variables to improve students' academic performance provide a solid basis for the design of effective educational strategies and highlight the potential of AI and ML to transform the educational sector.