Treffer: Human-AI Collaborative Feedback in Improving EFL Writing Performance: An Analysis Based on Natural Language Processing Technology

A perfect writing skill has been deemed instrumental to achieving competence in EFL, yet it is considered one of the most impressive learning domains. This study investigates the impact of human-AI collaborative feedback on the writing proficiency of EFL students. It examines key teaching domains, including the teaching environment, teacher knowledge and experience, and feedback quality and timeliness, focusing on language features such as accuracy, complexity, and fluency. This study employed a mixed-methods approach, integrating both quantitative and qualitative data. A stratified random sampling technique was utilised to select 260 EFL students from tertiary institutions for the survey, while purposive sampling was employed to recruit five participants for semi-structured interviews. Quantitative data were analysed using regression and mediation tests to examine the relationships between feedback and writing performance. In contrast, qualitative data were subjected to thematic analysis to explore participants' perceptions of the human-AI feedback mechanism. The findings indicate that human-AI collaborative feedback significantly enhances writing performance by delivering timely and detailed insights, thereby fostering improvements in language accuracy, complexity, and fluency. Additionally, writing enjoyment and cognitive competencies were identified as mediators in the relationship between feedback and writing improvement. The study highlights the potential of integrating AI into EFL feedback systems to complement existing approaches and foster more comprehensive improvements in EFL writing. The study acknowledges certain limitations, including its reliance on self-reported data, which may introduce biases in students' perceptions of their writing improvement.

As Provided