IMPLEMENTASI DEEP LEARNING MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK KLASIFIKASI GAYA BELAJAR SISWA BERDASARKAN EKSPRESI WAJAH SISWA SELAMA PROSES PEMBELAJARAN
DOI:
https://doi.org/10.55123/storage.v5i3.9163Keywords:
Deep Learning, Convolutional Neural Network, Ekspresi Wajah, Gaya Belajar, VARKAbstract
Perbedaan gaya belajar siswa menjadi tantangan bagi guru dalam menentukan metode pembelajaran yang tepat, terutama pada kelas dengan jumlah siswa yang besar. Penelitian ini bertujuan mengembangkan sistem analisis respons afektif dan estimasi kecenderungan gaya belajar siswa secara otomatis berdasarkan ekspresi wajah selama proses pembelajaran tatap muka menggunakan metode Convolutional Neural Network (CNN). Data dikumpulkan melalui perekaman video pembelajaran di kelas XI.A4 SMA Negeri 1 Kendari dan diproses menggunakan Haar Cascade dan CSRT untuk menghasilkan 1.652 citra wajah yang terbagi ke dalam empat kelas ekspresi yaitu Tertarik, Fokus, Bingung, dan Bosan. Proses pelabelan divalidasi oleh dua anotator independen dengan nilai Cohen's Kappa (κ = 0,8138) dan Gwet's AC1 (AC1 = 0,8323) yang termasuk kategori Almost Perfect Agreement. Model CNN yang dibangun dengan arsitektur empat blok konvolusi bertingkat menghasilkan akurasi sebesar 94,76% pada data pengujian. Hasil klasifikasi ekspresi selanjutnya dipetakan ke kecenderungan gaya belajar berdasarkan model VARK melalui mekanisme majority voting dan diimplementasikan dalam sistem berbasis web bernama EduFace yang memungkinkan guru menganalisis kecenderungan gaya belajar siswa secara otomatis dari video pembelajaran tanpa memerlukan observasi manual.
Downloads
References
Cohen, J., 1960, ‘A Coefficient of Agreement for Nominal Scales’, Educational and Psychological Measurement, 20(1), 37–46.
Ekman, P. & Friesen, W. V, 1978, Facial Action Coding System: Manual.
Fleming, N.D. & Mills, C., 1992, ‘Not Another Inventory, Rather a Catalyst for Reflection’, To Improve the Academy, 11, 137–155.
Gambo, F.L., Wajiga, G.M., Garba, E.J. & Abdullahi, A.A., 2020, ‘Prediction of Learning Style Using Facial Expressions with Convolutional Neural Network Special Issue on Computing and Communication Technologies Prediction of Learning Style Using Facial Expressions with Convolutional Neural Network’, International Journal of Information Processing and Communication (IJIPC), 9(2), 389–399.
Govindwar, V., Aman Akbani, Aachal Nandeshwar, Aishwarya Wanjari, Prachi Agashe & Charan Pote, 2024, ‘Facial Expression Recognition Using Convolutional Neural Network’, International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(2), 786–794.
Gupta, S., Kumar, P. & Tekchandani, R.K., 2023, ‘Facial emotion recognition based real-time learner engagement detection system in online learning context using deep learning models’, Multimedia Tools and Applications, 82(8), 11365–11394.
Hu, X. & Gao, J., 2025, Facial expression recognition reveals students’ engagement in online class: Correlations with six engagement measurements, PLOS One, 1–22, Public Library of Science.
Irawan, Y., 2025, ‘Analisis Kesulitan Guru dalam Menerapkan Pembelajaran Berdiferensiasi di Kelas Inklusif’, Makarimul Ilmi: Jurnal Pengembangan Madrasah Ibtidayah, 02(02), 97–108.
Lek, J.X.-Y. & Teo, J., 2023, ‘Academic Emotion Classification Using FER: A Systematic Review’, Human Behavior and Emerging Technologies, 2023, 1–27.
Musa, L. & Kumalasari, D., 2024, ‘Implementasi Pembelajaran Berdiferensiasi dalam Upaya Pemenuhan Kebutuhan Belajar Murid pada Mata Pelajaran IPS’, Ideguru: Jurnal Karya Ilmiah Guru, 9(2), 809–814.
Pabba, C. & Kumar, P., 2022, ‘An intelligent system for monitoring students’ engagement in large classroom teaching through facial expression recognition’, Expert Systems, 39(1).
Sasmita, P.R. & Hartoyo, Z., 2020, ‘Pengaruh Pendekatan Pembelajaran STEM Project Based Learning terhadap Pemahaman Konsep Fisika Siswa’, SILAMPARI Jurnal Pendidikan Ilmu Fisika, 2(2), 136–148.
Suryani, E.A., Siswanto, D.H., Pisriwati, S.A. & History, A., 2024, ‘Strengthening Teacher Competence through Differentiated Instruction Training as an Implementation of the Merdeka Curriculum Article Info ABSTRACT’, JOELI: Journal of Educational and Learning Innovation, 1(2), 3063–3966.
Tonguç, G. & Ozaydın Ozkara, B., 2020, ‘Automatic recognition of student emotions from facial expressions during a lecture’, Computers & Education, 148, 103797.
Viola, P. & Jones, M., 2001, Rapid object detection using a boosted cascade of simple features, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, I-511-I–518, IEEE Comput. Soc.
Whitehill, J., Serpell, Z., Lin, Y.-C., Foster, A. & Movellan, J.R., 2014, ‘The Faces of Engagement Automatic Recognition of Student Engagement from Facial Expressions’, IEEE Transaction on Affective Computing, 5(1), 86–98.
Wongpakaran, N., Wongpakaran, T., Wedding, D. & Gwet, K.L., 2013, ‘A comparison of Cohen’s Kappa and Gwet’s AC1 when calculating inter-rater reliability coefficients: a study conducted with personality disorder samples’, BMC Medical Research Methodology, 13(1), 61.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 sherly dwi puspita, Sutardi, L.M. Golok Jaya, L.M. Bahtiar Aksara, Andi Tenriawaru, Isnawaty
This work is licensed under a Creative Commons Attribution 4.0 International License.
