Artificial Intelligence as a Tool for Personalizing English as a Second Language Learning: A Systematic Literature Review
The teaching of English as a Second Language (ESL) has traditionally relied on standardized pedagogical approaches that often fail to address learners’ diverse proficiency levels, learning paces, and communicative needs. This limitation has highlighted the need for personalized learning, particularly given the non linear and heterogeneous nature of language acquisition. However, conventional instructional models have shown constraints in providing individualized support and continuous feedback, especially in large or resource limited educational settings. In this context, artificial intelligence has evolved from a supplementary tool into a pedagogical infrastructure capable of supporting personalized learning processes. This study conducted a systematic literature review following the PRISMA protocol, analyzing peer reviewed publications from 2020 to 2025 to examine how AI technologies are being used to adapt learning trajectories, automate formative assessment, and enhance learner autonomy in ESL contexts. The findings were organized into three main categories: adaptive learning systems, generative AI for text production and language interaction, and automated assessment tools with immediate feedback. The results showed that AI supported environments facilitate the development of Adaptive Learning Paths, individualized practice, and scalable feedback mechanisms. These effects were particularly evident in writing, vocabulary acquisition, and grammatical accuracy, with emerging contributions to communicative competence through AI mediated interaction. The study concludes that the educational value of artificial intelligence in ESL depends not solely on its technological capabilities, but on its integration with pedagogical design, teacher mediation, and ethical implementation. Under this perspective, AI should be understood as a complementary resource that enhances, rather than replaces, the educational process.
Paper
The full text of this publication is not hosted on 44B due to licensing.
Read it at OpenAlex