Development of a Computer Vision-Based Instrument for Assessing Mindful, Meaningful, and Joyful Learning in Elementary Schools

Authors

  • Tegar Baradika Putra Karunia Universitas Sains Al-Qur'an Author
  • Muhammad Hanif Universitas Pendidikan Indonesia Author
  • Dian Asmarajati Universitas Sains Al-Qur'an Author
  • Iman Aahmad Ihsanudin Universitas Sains Al-Qur'an image/svg+xml Author
  • Budi Setiawan Universitas Pendidikan Indonesia Author
  • Aan Khosihan Universitas Pendidikan Indonesia Author

DOI:

https://doi.org/10.17509/theq2p18

Keywords:

Computer Vision, Deep Learning, Pedagogical Learning Assessment

Abstract

The Deep Learning approach (Mindful, Meaningful, Joyful) is a student-centered pedagogical framework adopted in Indonesia’s Merdeka Belajar curriculum. However, the lack of objective, scalable assessment instruments remains a significant challenge. This study aimed to develop and validate EduClassify, a Computer Vision-based assessment instrument for deep learning in elementary schools. Using the ADDIE R&D model, the system was evaluated across 28 classroom observation sessions. EduClassify integrates four Computer Vision models (YOLOv8, MediaPipe, DeepFace, and gaze tracking) to detect indicators across all 3M dimensions automatically. Results showed that 66.7% of classes met the ‘Fairly Good’ category (score  50). Meaningful Learning showed the strongest correlation with the overall Deep Learning score (r = 0.847). A strong positive correlation was also found between student talk time and Meaningful score (r = 0.910), confirming student-centered interaction as the primary driver of meaningful learning. Reliability testing using Cronbach’s Alpha yielded α = 0.722 (Mindful) and α = 0.748 (Meaningful), whereas Joyful scored α = 0.031 due to rear-angle camera limitations. This study demonstrates the instrument’s feasibility and provides empirical recommendations for multi-camera configurations in future implementations. Practically, this instrument enables school leaders to conduct data-driven clinical pedagogical supervision and targeted instructional coaching.

References

Adeoye, M. A., Wirawan, K. A. S. I., Pradnyani, M. S. S., & Septiarini, N. I. (2024). Revolutionizing education: Unleashing the power of the ADDIE model for effective teaching and learning. Jurnal Pendidikan Indonesia, 13(1), 202–209. https://doi.org/10.23887/jpiundiksha.v13i1.68624

Alruwais, N., & Zakariah, M. (2023). Student-engagement detection in classroom using machine learning algorithm. Electronics, 12(3), 731. https://doi.org/10.3390/electronics12030731

Bentz, V. M. (1992). Deep learning groups: Combining emotional and intellectual learning. Clinical Sociology Review, 10(1), 71–89. https://digitalcommons.wayne.edu/csr/vol10/iss1/9/

Bredin, H., Yin, R., Coria, J. M., Broux, G., Hadjimarkou, P. A., Bennaceur, M., ... & Gill, M. P. (2020). Pyannote.audio: Neural building blocks for speaker diarization. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 7124-7128). IEEE. https://doi.org/10.1109/ICASSP40776.2020.9052974

George, D., & Mallery, P. (2020). IBM SPSS Statistics 26 Step by Step: A Simple Guide and Reference (16th Ed.). Routledge. https://doi.org/10.4324/9780429056765

Gupta, S., Kumar, P., & Tekchandani, R. (2023). A multimodal facial cues based engagement detection system in e-learning context using deep learning approach. Multimedia Tools and Applications, 82, 28589–28615. https://doi.org/10.1007/s11042-023-14392-3

Jin, R., Peng, Y., Wang, Z., Wang, J., Tang, J., & Zhang, M. (2025). Data-driven educational decision-making: How to enhance educational quality and management efficiency. Journal of Higher Education Research, 5(6), 550-553. https://doi.org/10.32629/jher.v5i6.3385

Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Michael, K., Xie, T., Fang, J., Yifu, Z., … & Jain, M. (2022). Ultralytics YOLO: YOLOv5 SOTA Realtime Instance Segmentation (Version v7.0) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.7347926

Kovač, V. B., Nome, D. Ø., Jensen, A. R., & Skreland, L. L. (2025). The why, what and how of deep learning: Critical analysis and additional concerns. Education Inquiry, 16(2), 237–253. https://doi.org/10.1080/20004508.2023.2194502

Lai, W-S., Shih, Y-C., Liang, C-K., & Yang, M-H. (2022). Correcting face distortion in wide-angle videos. IEEE Transactions on Image Processing, 31, 366-378. https://doi.org/10.1109/TIP.2021.3131047

Lin, L., Zhou, D., Wang, J., & Wang, Y. (2024). A Systematic Review of Big Data Driven Education Evaluation. Sage Open, 14(2). https://doi.org/10.1177/21582440241242180

Liu, Q., Jiang, X., & Jiang, R. (2025). Classroom behavior recognition using computer vision: A systematic review. Sensors, 25(2), 373. https://doi.org/10.3390/s25020373

Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C-L., Yong, M. G., …. & Grundmann, M. (2019). MediaPipe: A framework for building perception pipelines. arXiv, 1906, 08172. https://doi.org/10.48550/arXiv.1906.08172

Ngo, H.-H., Lin, F.-C., Sehn, Y.-T., Tu, M., & Dow, C.-R. (2020). A Room Monitoring System Using Deep Learning and Perspective Correction Techniques. Applied Sciences, 10(13), 4423. https://doi.org/10.3390/app10134423

Nursehag, D. A., & Amalia, L. L. (2024). An investigation of teacher talk and student talk in Indonesian EFL classroom interaction. Paedagogia: Jurnal Penelitian Pendidikan, 27(2), 298–308. https://doi.org/10.20961/paedagogia.v27i1.84086

Parsons, H. M. (1974). What happened at Hawthorne? Science, 183(4128), 922–932. https://doi.org/10.1126/science.183.4128.922

Peters, M. A. (2018). Deep learning, education and the final stage of automation. Educational Philosophy and Theory, 50(6–7), 549–553. https://doi.org/10.1080/00131857.2017.1355799

Pillai, A. S. (2022). Student engagement detection in classrooms through computer vision and deep learning: A novel approach using YOLOv4. Sage Science Review of Educational Technology, 5(1), 87–97. https://doi.org/10.5281/zenodo.15061626

Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2023). Robust speech recognition via large-scale weak supervision. Proceedings of Machine Learning Research, 202, 28492-28518. https://doi.org/10.5555/3618408.3619590

Serengil, S. I., & Ozpinar, A. (2020). LightFace: A hybrid deep face recognition framework. In 2020 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 23–27). IEEE. https://doi.org/10.1109/ASYU50717.2020.9259802

Spatioti, A. G., Kazanidis, I., & Pange, J. (2022). A comparative study of the ADDIE Instructional design model in distance education. Information, 13(9), 402. https://doi.org/10.3390/info13090402

Suyanto, S. (2025). Naskah Akademik Pembelajaran Mendalam Menuju Pendidikan Bermutu untuk Semua. Pusat Kurikulum dan Pembelajaran Badan Standar, Kurikulum, dan Asesmen Pendidikan Kementerian Pendidikan Dasar dan Menengah Republik Indonesia. https://repositori.kemendikdasmen.go.id/39385/

Szeliski, R. (2022). Computer Vision: Algorithms and Applications (2nd ed.). Springer. https://doi.org/10.1007/978-3-030-34372-9

Tal, T., & Tsaushu, M. (2018). Student-centered introductory biology course: evidence for deep learning. Journal of Biological Education, 52(4), 376–390. https://doi.org/10.1080/00219266.2017.1385508

Trabelsi, Z., Alnajjar, F., Parambil, M. M. A., Gochoo, M., & Ali, L. (2023). Real-time attention monitoring system for classroom: A deep learning approach for student’s behavior recognition. Big Data and Cognitive Computing, 7(1), 48. https://doi.org/10.3390/bdcc7010048

Vygotsky, L. S. (1978). Mind in Society: The Development of Higher Psychological Processes. Harvard University Press. https://doi.org/10.2307/j.ctvjf9vz4

Wang, C., Ding, Y., Cui, K., Li, J., Xu, Q., & Mei, J. (2025). A perspective distortion correction method for planar imaging based on homography mapping. Sensors (Basel), 25(6), 1891. https://doi.org/10.3390/s25061891

Xu, Q., Wei, Y., Gao, J., Yao, H., & Liu, Q. (2023). ICAPD framework and simAM-YOLOv8n for student cognitive engagement detection in classroom. IEEE Access, 11, 136063–136076. https://doi.org/10.1109/ACCESS.2023.3338721

Zhang, S., Yang, Y., Chen, C., Zhang, X., Leng, Q., & Zhao, X. (2024). Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: A systematic review of recent advancements and future prospects. Expert Systems with Applications, 237, 121692. https://doi.org/10.1016/j.eswa.2023.121692

Downloads

Published

2026-09-30

Issue

Section

Articles

How to Cite

Karunia, T. B. P., Hanif, M., Asmarajati, D., Ihsanuddin, I. A., Setiawan, B., & Khosihan, A. (2026). Development of a Computer Vision-Based Instrument for Assessing Mindful, Meaningful, and Joyful Learning in Elementary Schools. Didaktika, 6(3), 300-314. https://doi.org/10.17509/theq2p18