Deteksi Bias dalam Model Machine Learning untuk Prediksi Kelulusan Mahasiswa Berdasarkan Aktivitas Virtual Learning Environment
Main Article Content
Abstract
Revolusi digital yang cepat dalam pendidikan telah menempatkan Virtual Learning Environment (VLE) sebagai elemen penting dalam mengembangkan paradigma pembelajaran, yang sangat terlihat selama pandemi COVID-19. Penelitian ini menyelidiki dampak aktivitas siswa berbasis VLE dalam memprediksi keberhasilan akademik dan mengatasi bias dalam model machine learning yang digunakan untuk prediksi ini. Menggunakan Open University Learning Analytics Dataset (OULAD), penelitian ini mengintegrasikan teknik prapemrosesan data, pemilihan fitur, dan transformasi data untuk mengembangkan dataset yang komprehensif. Model Random Forest digunakan untuk memprediksi hasil kelulusan siswa, yang dikategorikan menjadi kelas "pass", "fail", dan "distinction". Kinerja model dievaluasi menggunakan metrik klasifikasi seperti akurasi, presisi, recall, dan F1-score, serta matriks kebingungan. Deteksi bias dilakukan menggunakan alat DALEX, dengan fokus pada atribut terlindungi seperti usia, jenis kelamin, dan disabilitas untuk memastikan keadilan. Hasilnya mengungkapkan akurasi model yang tinggi tetapi menyoroti adanya bias yang signifikan dalam beberapa kelompok demografis. Penelitian ini berkontribusi pada diskursus berkelanjutan tentang memastikan penerapan machine learning yang etis dan adil dalam pengaturan pendidikan dengan mengusulkan metode untuk meningkatkan kesetaraan dan transparansi model prediktif.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
A. H. A Rashid, N. A. Shukor, Z. Tasir, and S. N. Kew, "Teachers’ perceptions and readiness toward the implementation of virtual learning environment," IJERE (International Journal of Evaluation and Research in Education), vol. 10, no. 1, pp. 209–214, 2021, doi: 10.11591/ijere.v10i1.21014.
R. Yusny and G. I. Yasa, "Mengembangkan (Pembelajaran) blended learning dengan sistem lingkungan pembelajaran virtual (Vle) Di ptkin," Jurnal Ilmiah Islam Futura, vol. 19 no. 1, pp. 103–127, 2019, doi: 10.22373/jiif.v19i1.3707.
Y. A. Hambali, R. R. Putra, and Wahyudin, "Implementasi Metaverse menggunakan Aplikasi gather town untuk Pendidikan Jarak Jauh dengan Pendekatan Virtual Learning Environment," INFORMATION SYSTEM FOR EDUCATORS AND PROFESSIONALS : Journal of Information System, vol. 7, no.2, pp. 163–172, 2023, doi: 10.51211/isbi.v7i2.2039.
F. N. Andryas, A. Irmarahayu, and N. Bustamam, "Virtual learning environment and learning approach among pre-clinical undergraduate medical students during COVID-19 pandemic," The Indonesian Journal of Medical Education, vol. 11, no. 1, pp. 10–21, 2022, doi: 10.22146/jpki.63975.
P. A. Petare, M. Shamim, T. Gupta, R. Verma, and G. Singh, "Exploring the impact of virtual learning environments on student engagement and academic achievement," Journal of Survey in Fisheries Sciences, vol. 10, no. 1S, pp. 5912–5923, 2023, doi: 10.13140/RG.2.2.23223.91040.
B. Mandasari, "The impact of online learning toward students’ academic performance on business correspondence course," EDUTEC (Journal of Education and Technology), vol. 4, no. 1, pp. 98–110, 2020, doi: 10.29062/edu.v4i1.74.
P. Muljana and T. Luo, "Factors contributing to student retention in online learning and recommended strategies for improvement: A systematic literature review," Journal of Information Technology Education: Research, vol. 18, pp. 19–57, 2019, doi: 10.28945/4182.
A. Al-Azawei and M. A. Al-Masoudy, "Predicting learners' performance in virtual learning environment (VLE) based on demographic, behavioral and engagement antecedents," International Journal of Emerging Technologies in Learning (iJET), vol. 15, no. 09, pp. 60–75, 2020, doi: 10.3991/ijet.v15i09.12691.
M. S. Ahmad, A. H. Asad, and A. Mohammed, "A machine learning based approach for student performance evaluation in educational data mining," in 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), 2021, pp. 187–192, doi: 10.1109/miucc52538.2021.9447602.
N. Tomasevic, N. Gvozdenovic, and S. Vranes, "An overview and comparison of supervised data mining techniques for student exam performance prediction," Computers & Education, vol. 143, no. 103676, pp. 1–18, 2020, doi: 10.1016/j.compedu.2019.103676.
H. Waheed, S. Hassan, N. R. Aljohani, J. Hardman, S. Alelyani, and R. Nawaz, "Predicting academic performance of students from VLE big data using deep learning models," Computers in Human Behavior, vol. 104, no. 106189, 2020, doi: 10.1016/j.chb.2019.106189.
S. Rizvi, B. Rienties, and S. A. Khoja, "The role of demographics in online learning; A decision tree based approach," Computers & Education, vol. 137, pp. 32–47, 2019, doi: 10.1016/j.compedu.2019.04.001.
A. Al-Zawqari, D. Peumans, and G. Vandersteen, "A flexible feature selection approach for predicting students’ academic performance in online courses," Computers and Education: Artificial Intelligence, vol. 3, no. 100103, 2022, doi: 10.1016/j.caeai.2022.100103.
R. S. Baker and A. Hawn, "Algorithmic bias in education," International Journal of ArtificialIntelligence in Education, vol. 32, no. 4, pp. 1052–1092, 2021, doi: 10.35542/osf.io/pbmvz.
R. Fu, Y. Huang, and P. V. Singh, "AI and algorithmic bias: Source, detection, mitigation and implications," SSRN Electronic Journal, vol. 65, pp. 39–63, 2020, doi: 10.2139/ssrn.3681517.
K. Cachel, E. Rundensteiner, and L. Harrison, "MANI-rank: Multiple attribute and intersectional group fairness for consensus ranking," in 2022 IEEE 38th International Conference on Data Engineering (ICDE), 2022, pp. 1124–1137, doi: 10.1109/icde53745.2022.00089.
S. Alelyani, "Detection and evaluation of machine learning bias," Applied Sciences, vol. 11, no. 14, pp. 6271, 2021, doi: 10.3390/app11146271.
J. Gardner, C. Brooks, and R. Baker, "Evaluating the fairness of predictive student models through slicing analysis," in Proceedings of the 9th International Conference on Learning Analytics & Knowledge, 2019, pp. 225–234, doi: 10.1145/3303772.3303791.
S. Riazy, K. Simbeck, and V. Schreck, "Fairness in learning analytics: Student at-risk prediction in virtual learning environments," in Proceedings of the 12th International Conference on Computer Supported Education, 2020, pp. 15–25, doi: 10.5220/0009324100150025.
M. Verger, S. Lalle, F. Bouchet, and V. Luengo, "Is your model 'MADD'? A novel metric to evaluate algorithmic fairness for predictive student models," in Proceedings of the 16th International Conference on Educational Data Mining (EDM 2023), 2023, doi: 10.5281/zenodo.8115786.
S. Riazy and K. Simbeck, "Predictive algorithms in learning analytics and their fairness," Lecture Notes in Informatics (LNI) - Proceedings, 2019, pp. 223–228, doi: 10.18420/delfi2019_305.
J. Wiśniewski and P. Biecek, "Fairmodels: A flexible tool for bias detection, visualization, and mitigation in binary classification models," The R Journal, vol. 14, no. 1, pp. 227–243, 2022, doi: 10.32614/rj-2022-019.
J. Kuzilek, M. Hlosta, and Z. Zdrahal, "Open University Learning Analytics dataset," Sci. Data, vol. 4, No. 170171, pp. 1–8 , 2017, doi: 10.1038/sdata.2017.171.
H. Baniecki, W. Kretowicz, P. Piatyszek, J. Wisniewski, and P. Biecek, "dalex: Responsible Machine Learning with Interactive," Journal of Machine Learning Research, vol. 22, pp. 1–7, 2021, doi: 10.48550/arXiv.2012.14406.
H. A. Mengash, "Using data mining techniques to predict student performance to support decision making in university admission systems," IEEE Access, vol. 8, pp. 55462–55470, 2020, doi: 10.1109/ACCESS.2020.2981905.
S. Alija, E. Beqiri, A. S. Gaafar, and A. K. Hamoud, "Predicting students performance using supervised machine learning based on imbalanced dataset and wrapper feature selection," Informatica, vol. 47, no. 1, pp. 11–19, 2023, doi: 10.31449/inf.v47i1.4519.