European Journal of Education· 2026Q1
Evaluating the English Teaching System in Smart Universities Using K‐Means Clustering for Enhanced Student Engagement and Sustainable Development
- 0citations
- Q1SCImago
- 2026year
Short summary
A new framework using K-means clustering (K=3) with a Silhouette Score of 0.72 and DBI of 0.39 objectively identifies student engagement patterns in smart university English courses, enabling adaptive and personalized teaching strategies.
AI-generated from the title and abstract; the full text is not read.
Key points
- K-means clustering (K=3) was used to identify student engagement patterns in smart university English courses.
- The framework achieved a Silhouette Score of 0.72 and a Davies-Bouldin Index of 0.39, indicating effective cluster separation.
- The method objectively identifies engagement patterns without requiring labeled data.
- Findings support the development of adaptive, personalized, and sustainable English teaching strategies.
AI-generated from the title and abstract; the full text is not read.
Abstract
ABSTRACT The growing needs for quality English education in technology‐enhanced universities require evidence‐based assessment measures to promote learner engagement and sustainability. Technology‐Enhanced Learning ( TEL ) integrates digital technologies and online learning tools into English teaching to support interactive, flexible and personalized learning experiences. This study suggests a framework for measuring the effectiveness of English teaching systems using K‐means clustering to understand learner satisfaction and engagement patterns. In this method, the proposed framework lies in integrating unsupervised K‐means clustering with clustering validity measures to objectively identify student engagement patterns and support evidence‐based instructional decision‐making without requiring labelled data. The framework achieved an optimal cluster configuration with K = 3, validated by a Silhouette Score of 0.72 and a Davies–Bouldin Index ( DBI ) of 0.39, indicating well‐separated and compact clusters. These findings provide practical guidance for implementing adaptive, personalized and sustainable English teaching strategies in smart university environments. The proposed engagement‐based clustering framework also supports inclusive e‐learning by enabling personalized learning interventions and accessibility‐oriented educational strategies that can enhance participation among learners with diverse educational needs, including students with disabilities. The results demonstrate that the proposed model effectively captures diverse engagement patterns and supports the development of adaptive teaching strategies. These findings provide actionable insights to enhance student engagement, promote sustainable teaching practices and improve overall learning experiences through adaptive and blended instructional approaches. Future studies may investigate longitudinal engagement behaviuors to further optimize the teaching framework.
The authors' abstract, as published at the source. European Journal of Education, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Science Applications
Computer Science ApplicationsComputer Science