Artificial Intelligence in EFL Education in China: A Systematic Review of Trends, Gaps, and Future Directions (2015-2024)

This study conducts a systematic review of artificial intelligence in English as a Foreign Language teaching and learning in China from 2015 to 2024 based on 56 articles selected from Scopus, ScienceDirect, ERIC, and CNKI databases, highlighting emerging trends, unresolved gaps, and possible avenues for future research. The findings reveal that AI in EFL education in China is at an early yet fast-developing stage. Research designs are dominated by experimental studies, system or model design, and empirical studies, with the mixed method being the most common, while the qualitative method is neglected in experimental research. AI systems and platforms like ChatGPT and Pigai are widely discussed, but AI algorithms receive limited attention. Higher education and university students are the focus, whereas K12 participants, adult learners, policymakers, AI developers, and administrators are rarely involved. The most discussed language skills are speaking and writing. Language acquisition and affective or psychological states are the most studied learning outcomes, while contemporary competencies remain under-researched. AI’s role in enhancing English skills is well-documented, but its potential in administration, intelligent tutoring, and adaptation and personalization remains underexplored. The review offers an up-to-date landscape with valuable insights for academics, teachers, decision-makers, and AI technologists.