Research on Challenges and Strategies of Students' Adaptive Learning within AI

Abstract

It's acknowledged that an adaptive e-learning system can be efficient for users to conduct personalized learning in which learners could choose appropriate content and preferred models based on artificial intelligence (AI) recommendations. Nowadays, the rapid development of adaptive platforms, fueled by the evolution of machine learning and AI, incontestably brings innovative potential to the educational field. However, there are many unavoidable challenges followed by the swift process of integrating AI and other technologies into adaptive learning practices. Through the extensive review of previous research on adaptive e-learning and comprehensive analysis of their prominent outcomes, the paper focuses on exploring the challenges of adaptive learning within AI that students are facing and proposing possible solutions. It's found that adaptive learning is mainly experiencing the challenges involving how to avoid data bias and protect personal privacy, making continuous evaluations of users, lack of emotion monitoring and technological support for both students and teachers and the technology integration and inequity. To deal with the increasing problems, some practical strategies are presented, such as properly governing data for learning management, conducting continuous evaluation and prediction for users, and visualizing cognition, which can be supportive of students' professional development in adaptive learning.