An Adaptive Learning Path Optimization Model for Advanced English Learners

Abstract

The advent of the big data era has triggered a major change in teaching methods, and personalized learning based on adaptive learning platforms with big data analysis technology has become a new paradigm of education technology. Firstly, the basic information characteristics of learners are described, and the learner characteristic model is constructed with cognitive level, learning style, learning emotion, and learning ability. At the same time, the framework construction of the learning path method is completed based on the knowledge map. On this basis, the adaptive learning path system improved based on a genetic algorithm was used to characterize the higher-order English learners, and then the clustering algorithm was used to analyze the characteristics of the higher-order English learners by clustering analysis. Eight clustering variables were selected to divide the learners into four categories. The first category of the “excellent learners” scored very high in the eight elements, indicating that the learners had a very high score in the adaptive learning path. The first category, “excellent learners”, scored high on all eight elements, indicating that the learners have strong learning abilities in the adaptive learning path. In order to verify the effect of the learning path on students’ academic performance, a pre-and post-test was conducted, and the difference in the mean values reflected that the learning path system has a significant effect on the improvement of performance. The learners’ perception of the system’s usefulness and ease of use resulted in F-values of 9.539 and 5.856, respectively, and the Sig. The values are 0.005 and 0.016, which are less than 0.05, and there is a significant difference. It indicates that the optimized adaptive learning path is highly recommended for use among higher-order English learners.