การวิเคราะห์พฤติกรรมการมีส่วนร่วมของผู้เรียนจากวีดิโอชั้นเรียนโดยใช้ปัญญาประดิษฐ์

Thong-oon Manmai; Danupon  Suebsurmran; Payungsak Kongsila; Paweena  Chamking; Akekathed Sanglub

Authors

Thong-oon Manmai Mathematics Program, Faculty of Education and Human Development, Sisaket Rajabhat University
Danupon Suebsurmran General Science Program, Faculty of Education and Human Development, Sisaket Rajabhat University
Payungsak Kongsila General Science Program, Faculty of Education and Human Development, Sisaket Rajabhat University
Paweena Chamking Computer Education Program, Faculty of Education and Human Development, Sisaket Rajabhat University
Akekathed Sanglub Computer Education Program, Faculty of Education and Human Development, Sisaket Rajabhat University

Keywords:

Student Behaviors, Classroom Learning Videos, Artificial Intelligence, Behavioral Codebook, Learning Analytics

Abstract

This study aimed to (1) analyze student behaviors in classroom learning videos using artificial intelligence (AI) and (2) examine the frequency and distribution of student behaviors by grade level and lesson time. The research data comprised learning videos of 227 students from nine classrooms, Grades 1–9, at Thetsaban 1 (Wat Chiang-i) School, Mueang Si Sa Ket District, Si Sa Ket Province, Thailand. The videos were segmented into 4,782 short clips, with one clip representing one target behavior. A Behavioral Codebook classified behaviors as B01 hand raising, B02 writing, B03 interaction with the teacher, and B04 interaction with peers. Gemini AI was used for classification, and human evaluators verified the results.

The results showed that B04 was most frequent (2,039 clips, 42.64%), followed by B02 (1,557 clips, 32.56%), B03 (615 clips, 12.86%), and B01 (571 clips, 11.94%). The 11–20-minute period had the highest number of behavioral clips. AI classifications agreed with human evaluators for all 4,782 clips (100.00%).

References

กระทรวงศึกษาธิการ. (2566). แนวทางการจัดการเรียนรู้ฐานสมรรถนะ. กระทรวงศึกษาธิการ.

สถาบันทดสอบทางการศึกษาแห่งชาติ. (2565). รายงานผลการประเมินคุณภาพผู้เรียนระดับชาติ. สถาบันทดสอบทางการศึกษาแห่งชาติ.

Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., … Liang, P. (2021). On the opportunities and risks of foundation models. Stanford Center for Research on Foundation Models.

Cai, T., Xiong, Y., He, C., Wu, C., & Cai, L. (2025). Classroom teacher behavior analysis: The TBU dataset and performance evaluation. Computer Vision and Image Understanding, 257, 104376.

Curby, T. W., Brock, L. L., & Hamre, B. K. (2013). Teachers' emotional support consistency predicts children's achievement gains and social skills. Early Education and Development, 24(3), 292–309.

Downer, J. T., Rimm-Kaufman, S. E., & Pianta, R. C. (2007). How do classroom conditions and children's risk for school problems contribute to children's behavioral engagement in learning? School Psychology Review, 36(3), 413–432.

Fredricks, J. A., Blumenfeld, P. C., & Paris, A. H. (2004). School engagement: Potential of the concept, state of the evidence. Review of Educational Research, 74(1), 59–109.

Gaudin, C., & Chaliès, S. (2015). Video viewing in teacher education and professional development: A literature review. Educational Research Review, 16, 41–67.

Google. (2025). Gemini API documentation: Video understanding. https://ai.google.dev/

Hidson, E. (2018). The complete guide to lesson observation. John Catt Educational.

Khalil, M., Topali, P., Ortega-Arranz, A., Er, E., Akçapınar, G., & Belokrys, G. (2024). Video analytics in digital learning environments: Exploring student behaviour across different learning contexts. Technology, Knowledge and Learning, 29(4), 1877–1905.

Pianta, R. C., & Hamre, B. K. (2009). Conceptualization, measurement, and improvement of classroom processes: Standardized observation can leverage capacity. Educational Researcher, 38(2), 109–119.

Reid, M., et al. (2024). Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv.

Sideridis, G. D. (1998). Direct classroom observation: Potential problems and solutions. Research in Education, 59(1), 19–28.

Volpe, R. J., Hill, E., Briesch, A. M., & Leiwant, I. (2025). Classroom observation of student behavior: A review of seven observation codes. School Psychology Review, 54(1), 105–127.

Wang, Z., Li, L., Zeng, C., Dong, S., & Sun, J. (2025). SLBDetection-Net: Towards closed-set and open-set student learning behavior detection in smart classroom of K-12 education. Expert Systems with Applications, 260, 125392.

Wilhelm, A. G., Gillespie Rouse, A., & Jones, F. (2018). Exploring differences in measurement and reporting of classroom observation inter-rater reliability. Practical Assessment, Research & Evaluation, 23(4).

Yu, Z., Xie, M., Gao, J., Liu, T., & Fu, Y. (2024). From raw video to pedagogical insights: A unified framework for student behavior analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 38(21), 23241–23249.

Zheng, Q., Chen, Z., Wang, M., Shi, Y., Chen, S., & Liu, Z. (2024). Automated multimode teaching behavior analysis: A pipeline-based event segmentation and description. IEEE Transactions on Learning Technologies, 17, 1717–1733.