Leveraging Smart Campus Data to Improve Teaching Quality: Insights on Teaching Evaluations

Ao Zhang (School of Management and Economics, The Chinese University of Hong Kong, Shenzhen, China)
Zhizhen Chen (School of Data Science, The Chinese University of Hong Kong, Shenzhen, China)
Ruizhi Liao (Guangdong Provincial Key Laboratory of Mathematical Foundations for Artificial Intelligence, School of Humanities & Social Science, The Chinese University of Hong Kong, Shenzhen, China)

Acta Pedagogia Asiana
Volume 5 - Issue SI - 2026

In higher education, student evaluations play a crucial role in assessing teaching quality. However, these evaluations areofteninfluenced byextraneous factors, e.g., false high-grade expectations indicated by course instructors. While previous research has extensively examined the long-term implications of grade inflation, the immediate impact of students' expectations for higher grades on their teaching evaluations has been less explored. This paper leverages smart campus data from The Chinese University of Hong Kong, Shenzhen, coveringthe periodfrom 2018 to 2020, to addressthis gap. By selecting four representative indicators, we investigate their potential to enhance teaching quality through student evaluations. Our analysis reveals that integrating additional data on student life and academic performance from Smart Campus systems can help identify key factors influencing students’ expected grades. This, in turn, allows for more precise adjustments to teaching evaluation results, pave the way to develop AI models aimed at enhancing the accuracy and reducing the incredibility of student evaluation of teaching.