Student Engagement Detection Based on Visual Behavior Indicators Using YOLOv8 on a Public Classroom Dataset
DOI:
https://doi.org/10.65475/sser8h18Keywords:
student engagement, YOLOv8, object detection, classroom analytics, behavioral engagement, deep learningAbstract
Student engagement is an important indicator for evaluating the quality of the learning process; however, its measurement in conventional classrooms still largely relies on subjective and labor-intensive manual observation. This study aims to establish a reproducible baseline for student engagement detection based on visual behavioral indicators using the YOLOv8 model on a public dataset. The working dataset was constructed from two subsets of the Student Class Behavior (SCB) Dataset and restructured into five behavioral classes: hand_raising, reading, writing, bowing_head, and turn_head, resulting in 9,274 image-label pairs split into 6,491 training, 1,854 validation, and 929 test samples. The experiment used YOLOv8n with an image size of 416, a batch size of 8, and 50 effective epochs in Google Colab. Performance was evaluated using precision, recall, mAP@0.5, and mAP@0.5:0.95. The results show that the model achieved a precision of 0.4429, a recall of 0.5393, mAP@0.5 of 0.4630, and mAP@0.5:0.95 of 0.3211. The best class-level performance was observed for writing (AP 0.635) and hand_raising (AP 0.597), while bowing_head (AP 0.288) and turn_head (AP 0.332) remained comparatively weak. These findings indicate that YOLOv8n is feasible as a reproducible baseline for visual student behavior detection, although annotation refinement, comparative experiments, and architectural optimization are still required to strengthen the scientific contribution and the feasibility of real-world classroom deployment
Downloads
References
[1] I. Qarbal, N. Sael, and S. Ouahabi, “Student’s Engagement Detection Based on Computer Vision: A Systematic Literature Review,” IEEE Access, vol. 13, pp. 140519–140545, 2025, doi: 10.1109/ACCESS.2025.3596885.
[2] N. Mahmood, S. M. Bhatti, H. Dawood, M. R. Pradhan, and H. Ahmad, “Measuring Student Engagement through Behavioral and Emotional Features Using Deep-Learning Models,” Algorithms, vol. 17, no. 10, p. 458, Oct. 2024, doi: 10.3390/a17100458.
[3] M. Bustos-López, N. Cruz-Ramírez, A. Guerra-Hernández, L. N. Sánchez-Morales, N. A. Cruz-Ramos, and G. Alor-Hernández, “Wearables for Engagement Detection in Learning Environments: A Review,” Biosensors, vol. 12, no. 7, p. 509, Jul. 2022, doi: 10.3390/bios12070509.
[4] B. Díaz and M. Nussbaum, “Artificial intelligence for teaching and learning in schools: The need for pedagogical intelligence,” Computers & Education, vol. 217, p. 105071, Aug. 2024, doi: 10.1016/j.compedu.2024.105071.
[5] H. Chen, G. Zhou, and H. Jiang, “Student Behavior Detection in the Classroom Based on Improved YOLOv8,” Sensors, vol. 23, no. 20, p. 8385, Oct. 2023, doi: 10.3390/s23208385.
[6] J. Zhang, L. Guo, and X. Wang, “Student Classroom Behavior Recognition Based on YOLOv8 and Attention Mechanism,” Information, vol. 16, no. 11, p. 934, Oct. 2025, doi: 10.3390/info16110934.
[7] Z. Trabelsi, F. Alnajjar, M. M. A. Parambil, M. Gochoo, and L. Ali, “Real-Time Attention Monitoring System for Classroom: A Deep Learning Approach for Student’s Behavior Recognition,” BDCC, vol. 7, no. 1, p. 48, Mar. 2023, doi: 10.3390/bdcc7010048.
[8] X. Sheng, S. Li, and S. Chan, “Real-time classroom student behavior detection based on improved YOLOv8s,” Sci Rep, vol. 15, no. 1, p. 14470, Apr. 2025, doi: 10.1038/s41598-025-99243-x.
[9] B. Prasetio and N. Pratiwi, “Deteksi Sampah Organik dan Anorganik Menggunakan Model YOLOv8,” jipi. jurnal. ilmiah. penelitian. dan. pembelajaran. informatika., vol. 10, no. 1, pp. 494–506, Jan. 2025, doi: 10.29100/jipi.v10i1.5965.
[10] Visen and N. Charibaldi, “Penerapan Object Detection Menggunakan Deep Learning Yolov8 Untuk Mengidentifikasi Sampah Anorganik (Maksimal Sepuluh Objek) Dalam Satu Citra,” JTIIK, vol. 12, no. 1, pp. 195–202, Feb. 2025, doi: 10.25126/jtiik.20251219012.
[11] V. Hendriko and D. Hermanto, “Performance Comparison of YOLOv10, YOLOv11, and YOLOv12 Models on Human Detection Datasets,” Brilliance, vol. 5, no. 1, pp. 440–450, Jul. 2025, doi: 10.47709/brilliance.v5i1.6447.
[12] S. Helmiyah, “Perancangan Sistem Deteksi Emosi Mahasiswa Pada Jam Perkuliahan Menggunakan Metode Yolo,” JATISI, vol. 12, no. 1, Mar. 2025, doi: 10.35957/jatisi.v12i1.10195.
[13] M. Adiastoro, Febry Putra Rochim, and S. Hidayat, “PERFORMANCE EVALUATION OF RECENT YOLO VERSIONS FOR CLASSROOM STUDENT BEHAVIOR DETECTION,” jitk, vol. 11, no. 4, pp. 1061–1074, May 2026, doi: 10.33480/jitk.v11i4.7773.
[14] Q. Jia and J. He, “Student Behavior Recognition in Classroom Based on Deep Learning,” Applied Sciences, vol. 14, no. 17, p. 7981, Sep. 2024, doi: 10.3390/app14177981.
[15] Resa Pramudita, Mochamad Rizal Fauzan, Ilyasa Nafan Faza, Jaja Kustija, Ibnu Hartopo, and Muhammad Adli Rizqulloh, “Student Behavior Detection Using YOLOv10 for Classroom Engagement Analysis,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi, vol. 15, no. 2, pp. 91–98, May 2026, doi: 10.22146/jnteti.v15i2.24611.
[16] C. Feng, Z. Luo, D. Kong, Y. Ding, and J. Liu, “IMRMB-Net: A lightweight student behavior recognition model for complex classroom scenarios,” PLoS ONE, vol. 20, no. 3, p. e0318817, Mar. 2025, doi: 10.1371/journal.pone.0318817.
[17] H. Achmad, A. Pramudwiatmoko, M. Satrio Gumilang, B. Al Karim, and H. Wiyono, “Analisis Kinerja Model Deteksi Objek Yolo, Ssd, dan Faster R-Cnn pada Citra Penglihatan Malam untuk Pengenalan Tindak Kejahatan,” JTIIK, vol. 12, no. 1, pp. 145–152, Feb. 2025, doi: 10.25126/jtiik.2025128409.
[18] D. S. Mahardhika and M. A. I. Pakereng, “Deteksi Objek Secara Real-Time Berbasis YOLOv8 dan Algoritma DeepSORT,” jmcs, vol. 5, no. 1, pp. 671–686, Jan. 2026, doi: 10.37676/jmcs.v5i1.10038.
[19] F. Masykur, E. Kumalasari, A. Prasetyo, and M. Arifin, “A Resource-Efficient YOLO Framework via Discrete Wavelet Transform-Based Image Compression for Plant Disease Detection,” vol. 31, no. 2, pp. 447–454, 2026.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mohammad Bhanu Setyawan, Angga Prasetyo, Fauzan Masykur (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
