Evidence record · UDINUS · SDGs
- Unit
- Rektorat UDINUS
- Period
- 2025
- Goals
- Record
- 8627613c-3468-44b2-85dc-b22a50ddbfb5
- Published
- 2026-10-30
Universitas Dian Nuswantoro conducted an activity to develop an innovative assessment framework for classifying learning styles in higher education. The activity involved UDINUS researchers Santiko, Irfan; Soeprobowati, Tri Retnaningsih; Surarso, Bayu; Tahyudin, Imam; Hasibuan, Zainal Arifin; and Pee, Ahmad Naim Che. The activity addressed the view that learning achievement is affected by each person’s unique learning style and that assessment becomes complex when general elements such as VARK are considered together with environmental conditions, teacher effectiveness, and stakeholder policies.
The proposed framework uses multidimensionality while simplifying the assessed features. The simplified aspects are grouped into Method, Material, and Media, or 3M. Its dimensions are organized into five groups: Traditional, Enhance, Mobile, Ubiquitous, and Smart, forming the TEMUS framework. The dataset consisted of approximately 1200 respondents comprising students and lecturers, and was divided into test data and training data. Four models were trialled: Random Forest, SVM, Decision Tree, and K-Nearest. The results were interpreted using MSE, R-Square, Accuracy, Recall, Precision, and F1-Score.
Among the compared models, Random Forest produced the most optimal results, with MSE of 0.46, R Square of 0.99, Accuracy of 0.86, Recall of 0.86, Precision of 0.87, and F1 Score of 0.84. The findings state that the TEMUS Dimensional Framework can conduct classification and form a compatibility pattern between lecturers’ and students’ learning styles. According to the framework, teacher and student performance is considered suitable and effective when the 3M components are assessed similarly from both perspectives; otherwise, a review is conducted. This activity is framed as UDINUS’s contribution to SDG 4 through innovation in higher education learning assessment.