ORIGINAL RESEARCH article
Front. Educ.
Sec. Higher Education
Volume 10 - 2025 | doi: 10.3389/feduc.2025.1639581
Construction and Analysis of Student Comprehensive Quality Portraits Using an Improved Canopy-K-means Algorithm
Provisionally accepted
- Yunnan Normal University, Kunming, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
With the rapid advancement of educational informatization, mining the valuable information hidden in student comprehensive quality evaluation data to precisely guide student development has become a hot topic in educational management. This study proposes an improved Canopy-K-means algorithm. By introducing a dynamic threshold adjustment mechanism and a global search strategy, the proposed method adapts the Canopy partitioning to the actual data distribution -- overcoming the limitations of fixed thresholds -- and increases the probability of quickly finding the global optimal solution while reducing the risk of converging to a local optimum. Experiments conducted on the comprehensive quality evaluation data of 1,711 undergraduates from the College demonstrate that, compared with the PCA-GMM algorithm, the improved Canopy-K-means algorithm increases the Silhouette Coefficient from 0.639 to 0.731, elevates the Calinski-Harabasz Index from 1599.1 to 1860.1, and reduces the Davies-Bouldin Index from 0.597 to 0.361, thereby significantly enhancing clustering stability. The seven-dimensional feature portrait model constructed based on the clustering results reveals that 61.9% of the students exhibit the "Students with Strong Moral and Academic Foundations, but Deficient in Innovation and Practice" type -- indicating that while they perform well in Moral Development Quality, Professional Basic Quality, and Physical and Mental Basic Quality, they show obvious deficiencies in Social Practice Quality and Technological Innovation Quality. Based on these findings, the study proposes recommendations such as upgrading practical platforms, restructuring the curriculum system, and implementing personalized guidance mechanisms. These suggestions provide precise data support for decision-making by education administrators and hold significant value for promoting precision management in higher education.
Keywords: Comprehensive quality, Student portrait, Canopy-K-means algorithm, Educational big data, educational data mining
Received: 02 Jun 2025; Accepted: 14 Oct 2025.
Copyright: © 2025 Zou, Yuan, Zhong, Yu and Du. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Junzhen Du, dujunzhen@ynnu.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.