This paper has analyzed research trends on personalized learning by bibliometric analysis method through a study of 928 articles from the Scopus database. The following issues are investigated: (1) Development scale, growth trajectory and geographical distribution of the research; (2) Outstanding authors and works on Personalized Learning; (3) Outstanding magazines and books on the topic; (4) Key themes found in these documents, and (5) Prominent methods/technologies used for personalized learning. Research results show that personalized learning is a fascinating topic in education and has been overgrown in recent years. Many researches on personalized learning comes from countries such as the United States and China. Our bibliometric analysis has revealed the main themes in the research works on Personalized Learning, such as artificial intelligence, learning style, and learning technology. The research has observed cognitive aspects of learners like knowledge level, learning style, preferences, etc. In most cases, the recommended tools and methods combined the content-based filtering, collaborative filtering, ontological approaches, etc. In addition, future research goals, difficulties, and concerns are highlighted in our work by examining the trends in several personalized learning elements.

Learning styles play a vital role in determining an individual student's best learning methods and suitable types of learning materials. Based on a survey that collects information about learners' learning styles in offline and online environments, chosen from Felder-Silverman Learning Style Model (FSLM) and David Kolb Learning Style Model, we have developed a model to group students based on their characteristics. Specifically, the data collected from 546 learners in 2 universities in Vietnam are put into clustering using the K-Means algorithm, then labelled and classified by Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) algorithm, and finally evaluated based on precision, recall, and F1 score metric to find the number of suitable groups. The results show a new learning model with four different learning styles, each corresponding to a category in the FSLM and David Kolb model, with values on the accuracy, precision, recall, and f1 score equaling 96%. With the strength of combining the theory of all three different learning style models, along with a machine learning model with high accuracy on a rather large data set, the research results promise to make a positive contribution to the problem of personalized learning content, helping learners have the most effective learning experience.

In an era where diversity and digitalization significantly influence higher education, understanding and adapting to various learning preferences is crucial. This study comprehensively analyzes 394 scholarly articles from 1984 to 2022 using bibliometric methods, providing a dynamic overview of the research patterns in learning styles within higher education. We identified four stages of development during this period: 1984–1995 (Low-interest), 1996–2005 (Early development), 2006–2018 (Development), and 2019–2022 (Intensification). Our analysis highlights that the United States, the United Kingdom, and Australia were the top three leading publishers of research on learning styles in higher education. The results reveal three main topics of publications: educational technology, learning environments, and subject behaviors. This research not only identifies emerging research topics but also underscores the importance of adapting instructional strategies to diverse learning styles to enhance educational outcomes in higher education.