Revolutionizing Online Learning with Novel Approaches to Personalized Adaptive Education Systems

The focus of this work is on the new approach to adaptive education in the context of online learning with the goal of designing an individual learning environment for students. To achieve the goals set, the system employs a combination of the neural collaborative filtering and recurrent neural networks for adjusting learning material in real time based on students’ activity and achievements. The application of the model resulted to mean accuracy of 95%, with adaptive learners having a 85% course completion rate against the 65% of traditional learners. In addition, the option that received increased satisfaction score was user satisfaction which recorded a 4.9 satisfaction score. These results show the feasibility of the implemented adaptive systems that could revolutionize the online learning.