Design of the English Personalized Learning Path Recommendation Algorithm Based on MABPSO

With the continuous deep integration of information technology and educational applications, online learning has been widely used in the field of education. However, due to the low accuracy of the recommendation algorithm, the personalized learning path pushed by the existing online learning system is poorly matched to the needs of learners and cannot meet the current application requirements. In this paper, a modified adaptive binary particle swarm optimization (MABPSO) algorithm with mutation operator and nonlinear increase of inertia weight is proposed. Firstly, the knowledge points and time characteristics of learning resources in online learning environment are analyzed, and a personalized learning path recommendation model is constructed. Then, to solve the problem that binary particle swarm optimization (BPSO) algorithm is not easy to escape from the local optimal in the late optimization period, the MABPSO is designed to improve the convergence speed and convergence accuracy of the algorithm, so as to solve the problem of low precision of personalized learning path recommendation and improve the recommendation efficiency. Finally, the proposed MABPSO algorithm is simulated and compared with other existing algorithms. The experimental results show that the MABPSO algorithm in this paper has better ability of optimal solution, and improves the convergence accuracy and convergence speed of the algorithm.