Vol.14, No.2, May 2025.                                                                                                                                                                          ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

TEM Journal

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

Stress Level Classification Towards Student Learning Outcomes Using Support Vector Machine

I Gusti Putu Asto Buditjahjanto, Naim Rochmawati, Parama Diptya Widayaka

© 2025 I Gusti Putu Asto Buditjahjanto, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

Citation Information: TEM Journal. Volume 14, Issue 2, Pages 1429-1437, ISSN 2217-8309, DOI: 10.18421/TEM142-43, May 2025.

Received: 08 August 2024.

Revised:  23 December 2024.
Accepted: 19 February 2025.
Published: 27 May 2025.

Abstract:

This research aims to group stress factors that influence student learning outcomes in higher education and classify the level of student learning outcomes. This study conducted the factor analysis to group the psychological stress variables of students. The factor analysis results were then used as inputs to the Support Vector Machine (SVM) classifier while the student learning outcomes served as outputs. Then proceed with the training and testing of SVM to be able to classify student learning outcomes correctly. The study results indicated that 36 stress variables could be grouped into 7 stress factors using factor analysis, namely conflict, learning readiness, participation, workload, fairness, focusing, and suitability. Four levels were used to categorize the learning results of students, such as very good, good, fair, and poor. The accuracy and precision of the SVM classification values were 0.89 and 0.70, respectively. The SVM classification results showed better results in comparison to comparable methods of classification like Decision Trees, Random Forests, K-Nearest Neighbor (K-NN), Linear Discriminant Analysis (LDA), and Gaussian Naive Bayes (GNB). The implications of this research can be used to classify student learning outcomes based on stress factors that accompany them during their studies.

Keywords – Classification, stress level, SVM, learning outcome, factor analysis

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------