A Comprehensive Evaluation Mode for Higher Education Based on AHP-TOPSIS-EWM and Hierarchical Clustering

The higher education plays an important role in the development of a country. Research on this issue may serve as a reference for countries to build a healthy and sustainable higher education system. We reviewed the literature and created a dataset Higher Education Evaluation Dataset (HEED) for this problem based on the collected data and interpolation algorithms. Based on the Analytic Hierarchy Process (AHP) and the Entropy Weighting Method (EWM), we established the weights of the dimension and indicator layers, and then used the TOPSIS method to calculate the health score of the national higher education system, obtaining a model capable of assessing the health of higher education in any country. In addition, the combination of the subjectivity provided by the AHP and the objectivity of the EWM and TOPSIS methods results in better performance of the model evaluation. To verify the validity of the model, we clustered 20 countries using hierarchical clustering algorithm. We found that the clustering results are generally consistent with the ratings obtained from the model, verifying that the model is applicable to the higher education evaluation system. Finally, the paper summarizes the model, which combines subjective indicators with quantitative and objective data and is the first attempt to use such a model for higher education evaluation.