Mobile Generative AI Literacy and English Writing Self-Efficacy: The Role of AI Feedback Engagement in Higher Education

Abstract

This study examines the relationship between mobile Generative Artificial Intelligence (GenAI) literacy and English writing self-efficacy (EWSE) among university students, with AI feedback engagement (AFE) proposed as a mediating mechanism. Using a quantitative cross-sectional design, data were collected from 312 university students in China through validated self-report measures. Partial least squares structural equation modelling (PLS-SEM) was employed to test the proposed relationships and mediation effects. The results show that mobile GenAI literacy (MGL) significantly predicts AFE (β = 0.563, p < 0.001) and EWSE (β = 0.182, p = 0.003), while AFE significantly predicts writing self-efficacy (β = 0.478, p < 0.001). AFE partially mediates the relationship between MGL and writing self-efficacy, accounting for approximately 59.6% of the total effect. The model explains 41.2% of the variance in writing self-efficacy. These findings indicate that the educational value of MGL extends beyond technological competence, with active engagement in AI-generated feedback serving as an important mechanism for strengthening writing confidence. The study highlights the importance of pedagogical approaches that promote critical evaluation, reflective use, and meaningful engagement with AI feedback.