From Static to Adaptive: Evaluating the Efficacy of AI-Powered Personalized Learning Pathways in Integrated English Skills Development
Abstract
speaking, reading, writing) among non-English major undergraduates in China. Moving beyond the static, one-size-fits-all model of traditional
instruction, the research examines whether personalized learning pathways generated by AI algorithms can lead to superior learning outcomes
and engagement compared to conventional methods. A mixed-methods approach was employed, involving a 16-week quasi-experimental
study with a control group (n=60) receiving standard instruction and an experimental group (n=60) using an AI-powered adaptive learning
platform (a customized module integrating diagnostic assessments, personalized content, and intelligent feedback). Quantitative data included
pre- and post-tests of integrated skills and platform usage logs. Qualitative data were gathered from student interviews and reflective journals.
Results indicated a statistically significant improvement in the post-test scores of the experimental group, particularly in listening and writing skills. Analysis of engagement metrics and qualitative feedback revealed higher levels of motivation, self-directed learning behavior, and
perceived usefulness among students in the experimental condition. The study concludes that AI-powered personalization presents a viable
and effective strategy for addressing learner diversity in College English, though its success hinges on thoughtful pedagogical integration and
ongoing teacher facilitation. Challenges regarding over-reliance on technology and the need for holistic skill integration are discussed.
Keywords
Full Text:
PDFReferences
[1] Chen, X., Xie, H., & Hwang, G. J. (2021). A multi-perspective study on the effectiveness of an adaptive learning system in supporting
English language learning. Journal of Educational Computing Research, 59(2), 383-407.
[2] Li, M., & Wang, Y. (2022). The design and application of an adaptive learning model for college English writing based on big data.
Technology Enhanced Foreign Language Education, (5), 68-74.
[3] Huang, R., Liu, D., & Liu, J. (2023). Investigating the impact of an AI-based personalized learning platform on learner engagement and
achievement in a university English course. Interactive Learning Environments, 31(4), 2155-2172.
[4] Liu, M., & Liu, M. (2023). A meta-analysis of the effects of intelligent tutoring systems on language learning. Journal of Computer Assisted Learning, 39(1), 267-282.
[5] Zheng, Y., & Yu, S. (2023). Data-driven personalized learning paths in a college English listening course: An empirical study. Interactive
Learning Environments, 31(4), 2345-2360.
[6] Zhang, H., & Zou, D. (2022). A state-of-the-art review of the modes and effectiveness of AI in language learning (2020-2022). Journal
of China Computer-Assisted Language Learning, 2(1), 1-19.
DOI: http://dx.doi.org/10.70711/neet.v4i6.9510
Refbacks
- There are currently no refbacks.
