Generative AI–Enabled Web-Based Personalized Learning Pathways in University English Education

Abstract

This study proposes a generative artificial intelligence (AI) framework for personalized learning pathways in web-based college English teaching. By integrating behavioral data, continuous feedback loops, and adaptive pathway adjustments, the framework aims to better meet learners' dynamic needs. Through a three group comparison of a traditional pathway and two AI-supported adaptive pathways, results in learner satisfaction, progress, behavioral complexity, and feedback latency indicated that AI-enabled pathways significantly improve overall learning performance and satisfaction, especially in high-demand contexts, with the highly personalized configuration yielding the strongest gains in progress and the lowest proportion of low performing learners, though they also reveal varied adaptation patterns among students. The study offers practical insights for designing adaptive web-based learning systems and contributes to the discourse on human–AI collaboration in language education.