Teaching Quality Evaluation based on Student’s Zone of Proximal Development (ZPD) Prediction

Abstract

The evaluation of teaching quality for university professors is a topic of common concern in the current reform of higher education evaluation. In light of the issues such as the lack of objective and scientific quantification in the majority of current university evaluations, as well as the significant manpower and time costs involved, a new approach for evaluating the teaching quality of university professors based on the students' Zone of Proximal Development (ZPD) is proposed. Firstly, the multidimensional data of university students are analyzed to identify the key factors related to the performance of a specific course. Machine learning algorithms are then used to predict the students' ZPD for that course. Secondly, by considering the difference between the predicted ZPD and the actual ZPD, taking into account the students' initial potential and their educational achievements, a more scientific evaluation of the professors' impact is conducted. The extent to which professors help students reach and surpass their ZPD, as well as expand their own potential, is measured to assess the teaching quality. By establishing an evaluation mechanism centered on the Contribution Index based on ZPD improvement, the predicted growth of students' ZPD is combined with their actual growth, quantifying the impact of professors' teaching quality in a meaningful way. This provides a more reliable and valid method for evaluating the teaching quality of university professors.