Examining the Effects of Ai-driven Learning Analytics on Personalized Feedback in Blended Higher Education Courses: Evidence From Nanjing Normal University, China
Year: 2026
Type: article
Study design: Observational Study
Abstract: The swift integration of Artificial Intelligence (AI) and Learning Analytics (LA) in higher education has opened the new opportunities to provide personalized feedback in scale blended learning. Nonetheless, the currently available literature is mostly focused on the efficiency of technologies and does not focus much on how students perceive and respond to AI-generated feedback. This paper examines the impacts of learning analytics powered by AI in the context of personalized feedback in blended classes of English as a Foreign Language (EFL) at Nanjing Normal University, China. The study applies a convergent mixed-methods design, which involves the quantitative analysis of LMS log data, surveys, and structural equation modeling along with qualitative analysis of feedback threads and semi-structured interviews with students and instructors. The article investigates the effects of AI-generated feedback on student engagement and feedback uptake, and academic performance, with the mediating impact of feedback literacy and a moderating effect of instructor mediation. The findings indicate that adaptive and personalized AI feedback is a significant way of stimulating behavioral engagement, increasing the use of feedback, and leading to improved learning results. Qualitative findings also indicate that the efficacy of AI feedback is determined by its specificity, actionability, and pedagogical relevance besides the ability of students to interpret feedback and the role of instructors in contextualizing it. The study, in general, points to the idea of AI-based feedback as a human-based pedagogical instrument instead of a strictly technological one, with valuable implications to the scalable and equitable application of AI in educational institutions.
Institution: Universitas Pendidikan Ganesha
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: diamond
OpenAlex ID: W7135185798
