Exploring the Role of AI-Enabled Personalized Learning Analytics in Enhancing EFL Grammar Acquisition: The Mediating Effects of Learner Engagement and the Moderating Role of Emotional Intelligence

This study tests whether AI-enabled personalized learning analytics (AI-PLA) improve EFL grammar acquisition in China and who benefits. A cross-sectional survey in four cities yielded N = 472 cases. AI-PLA quality was modeled as a higher-order construct; learner engagement and emotional intelligence (EI) served as mediator and moderator; grammar acquisition was assessed with the Oxford Placement Test Use-of-English score. SmartPLS 4 supported hierarchical modeling, a latent interaction, and diagnostics. AI-PLA quality directly predicted grammar (β = .19, p < .001) and strongly predicted engagement (β = .48, p < .001). Engagement predicted grammar (β = .41, p < .001) and mediated the AI-PLA → grammar link (β_indirect = .20, p < .001), indicating partial mediation. EI moderated the AI-PLA → engagement path (β_interaction = .12, p = .004). R 2 engagement = .56; R 2 grammar = .44. Theoretically, we link analytics quality—information quality, system quality, feedback timeliness, perceived personalization—to grammar outcomes through engagement and identify EI as a boundary condition. Practically, we recommend analytics that provide accurate error detection, feedback, usable interfaces, and visible personalization, alongside routines that cultivate engagement and emotion regulation.