Predicting Digital Literacy Levels in Higher Education: A LightGBM Model Integrating Feature Selection for Improved Accuracy
DOI:
https://doi.org/10.70609/g-tech.v9i4.8077Keywords:
Classification, Digital Literacy, Machine Learning, LightGBMAbstract
Digital literacy has become an essential skill in higher education, particularly in online and distance learning settings. This study explores the use of Light Gradient Boosting Machine (LightGBM) to classify digital literacy levels among 10,393 students at Universitas Terbuka. To improve both efficiency and clarity of interpretation, feature selection was carried out using SelectKBest, which reduced the dataset to 33 predictors. The final model, evaluated through stratified 5-fold cross-validation, achieved an accuracy of 0.964 and a weighted F1-score of 0.964. The results show that limiting the number of features did not weaken predictive performance, while also making it easier to identify which aspects of digital literacy are most influential. Interestingly, the strongest predictors were not only technical skills but also ethical behavior, digital citizenship, and online communication. These findings highlight that digital literacy is multidimensional and that effective assessment tools must account for social and behavioral factors alongside technical competence. Taken together, applying feature selection with LightGBM offers an effective way to assess digital literacy in higher education. The method achieves strong predictive accuracy while keeping the model interpretable, giving universities clearer guidance for shaping interventions and curricula in online learning contexts.
References
Audrin, C., & Audrin, B. (2022). Key factors in digital literacy in learning and education: a systematic literature review using text mining. Education and Information Technologies, 27(6), 7395–7419. https://doi.org/10.1007/s10639-021-10832-5
Bukonla, A. O. (2025). An Optimized Light-GBM Based Classification Model for Effective Classification of Loan Defaulter. Dutse Journal of Pure and Applied Sciences, 11(1b), 301–310. https://doi.org/10.4314/dujopas.v11i1b.32
Ca, B. U., & Fr, Y. G. (2004). No Unbiased Estimator of the Variance of K-Fold Cross-Validation Yoshua Bengio Yves Grandvalet. In Journal of Machine Learning Research (Vol. 5).
Deschênes, A. A. (2024). Digital literacy, the use of collaborative technologies, and perceived social proximity in a hybrid work environment: Technology as a social binder. Computers in Human Behavior Reports, 13. https://doi.org/10.1016/j.chbr.2023.100351
Falloon, G. (2020). From digital literacy to digital competence: the teacher digital competency (TDC) framework. Educational Technology Research and Development, 68(5), 2449–2472. https://doi.org/10.1007/s11423-020-09767-4
Friedman, J. H. (2001). Greedy Function Approximation: A Gradient Boosting Machine. In Source: The Annals of Statistics (Vol. 29, Issue 5).
He, T., & Zhu, C. (2017). Digital informal learning among Chinese university students: the effects of digital competence and personal factors. International Journal of Educational Technology in Higher Education, 14(1). https://doi.org/10.1186/s41239-017-0082-x
Ilomäki, L., Paavola, S., Lakkala, M., & Kantosalo, A. (2016). Digital competence – an emergent boundary concept for policy and educational research. Education and Information Technologies, 21(3), 655–679. https://doi.org/10.1007/s10639-014-9346-4
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 31st Conference on Neural Information Processing Systems (NIPS 2017). https://github.com/Microsoft/LightGBM.
Kharis, S. A. A., Arisanty, M., Permatasari, M., Robiansyah, A., & Sukatmi, S. (2025). Exploration of The Digital Literacy Level of New Students in Open and Distance Learning. Paedagoria : Jurnal Kajian, Penelitian Dan Pengembangan Kependidikan, 16(2), 259–266. https://doi.org/10.31764
Kharis, S. A. A., Hertono, G. F., Irawan, S. R., Wahyuningrum, E., & Yumiati. (2023). Students’ success prediction based on the Fuzzy K-Nearest Neighbor method in Universitas Terbuka. Education Technology in the New Normal: Now and Beyond, 212–218. https://doi.org/10.1201/9781003353423-22
Kharis, S. A. A., & Zili, A. H. A. (2022). Learning Analytics dan Educational Data Mining pada Data Pendidikan. Jurnal Riset Pembelajaran Matematika Sekolah, 6.
Kuhn, M., & Johnson, K. (2013). Applied Predictive Modeling. Springer.
Li, F., Cheng, L., Wang, X., Shen, L., Ma, Y., & Islam, A. Y. M. A. (2025). The causal relationship between digital literacy and students’ academic achievement: a meta-analysis. Humanities and Social Sciences Communications, 12(1). https://doi.org/10.1057/s41599-025-04399-6
Márquez-Vera, C., Romero Morales, C., & Ventura Soto, S. (2013). Predicting school failure and dropout by using data mining techniques. Revista Iberoamericana de Tecnologias Del Aprendizaje, 8(1), 7–14. https://doi.org/10.1109/RITA.2013.2244695
Martínez-Bravo, M. C., Chalezquer, C. S., & Serrano-Puche, J. (2022). Dimensions of Digital Literacy in the 21st Century Competency Frameworks. Sustainability (Switzerland), 14(3). https://doi.org/10.3390/su14031867
Permatasari, M., Kharis, A. A., Arisanty, M., Robiansyah, A., & Zubir, E. (2025). Validity and Reliability Testing of Student Digital Literacy Instrument in Distance Education. In Science and Technology ISST (Vol. 2024).
Romero, C., & Ventura, S. (n.d.). Educational Data mining and Learning Analytics: An updated survey.
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management, 45(4), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
Wang, Y., & Wang, T. (2020). Application of improved LightGBM model in blood glucose prediction. Applied Sciences (Switzerland), 10(9). https://doi.org/10.3390/app10093227
Wei, X., Saab, N., & Admiraal, W. (2021). Assessment of cognitive, behavioral, and affective learning outcomes in massive open online courses: A systematic literature review. Computers and Education, 163. https://doi.org/10.1016/j.compedu.2020.104097
Yadalam, P. K., Thirukkumaran, P. V., Natarajan, P. M., & Ardila, C. M. (2024). Light gradient boost tree classifier predictions on appendicitis with periodontal disease from biochemical and clinical parameters. Frontiers in Oral Health, 5. https://doi.org/10.3389/froh.2024.1462873
Zakir, S., Hoque, M. E., Susanto, P., Nisaa, V., Alam, M. K., Khatimah, H., & Mulyani, E. (2025). Digital literacy and academic performance: the mediating roles of digital informal learning, self-efficacy, and students’ digital competence. Frontiers in Education, 10. https://doi.org/10.3389/feduc.2025.1590274
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Arman Haqqi Anna Zili, Selly Anastassia Amellia Kharis
This work is licensed under a Creative Commons Attribution 4.0 International License.
