Efficient and accurate assessment of classroom learning engagement is crucial for dynamically tracking learning progress and improving teaching quality. However, existing research faces challenges such as limited analytical dimensions and insufficient model generalizability. To address these issues, this study, leveraging deep learning technologies, proposed an intelligent assessment method for classroom learning engagement that integrates both behavioral and emotional analysis. The method encompasses the entire process, including dataset construction, deep learning model training, model evaluation, application, and statistical analysis. The results demonstrate that the trained deep learning model exhibits exceptional accuracy and robustness in both behavioral and emotional analysis tasks. Through a case study of classroom video recordings from a specific class, this research further revealed the dynamic evolution of classroom learning engagement at both individual and collective levels, validating the method’s effectiveness and feasibility in real-world teaching contexts.
FREDRICKSJ A, BLUMENFELDP C, PARISA H. School engagement: Potential of the concept, state of the evidence[J]. Review of Educational Research, 2006, 74(1):59-109. DOI: 10.3102/00346543074001059 .
[2]
GUNUCS. The relationships between student engagement and their academic achievement[J]. International Journal on New Trends in Education and their Implications, 2014, 5(4):216-231. DOI: 10.2224/sbp.7054 .
[3]
JIAM L, WUZ X, REITERA, et al. Exploring visual engagement signals for representation learning[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). New York: IEEE Press, 2021: 4186-4197. DOI:10.1109/ICCV48922.2021.00417 .
[4]
XUY P, LIY Y, CHENY S, et al. Spontaneous visual database for detecting learning-centered emotions during online learning[J]. Image and Vision Computing, 2023, 136: 104739. DOI:10.1016/j.imavis.2023.104739 .
ZHAOC, SHUH, GUX Q. The measurement and analysis of students’ classroom learning behavior engagement based on computer vision technology[J]. Modern Educational Technology, 2021, 31(6):96-103. DOI: 10.3969/j.issn.1009-8097.2021.05.012(Ch ).
[7]
ASHWINT S, GUDDETIR M R. Unobtrusive behavioral analysis of students in classroom environment using non-verbal cues[J]. IEEE Access, 2019, 7: 150693-150709. DOI:10.1109/ACCESS.2019.2947519 .
WANK, RAOC R, XUR M. The focus and shift of the research on learning engagement in the field of international education[J]. Modern Educational Technology, 2021, 31(4): 36-43. DOI: 10.3969/j.issn.1009-8097.2021.04.005(Ch ).
[10]
ZHANX H, SUND E, WENY, et al. Investigating students’ engagement in mobile technology-supported science learning through video-based classroom observation[J]. Journal of Science Education and Technology, 2022, 31(4): 514-527. DOI:10.1007/s10956-022-09970-3 .
[11]
ZHENGZ J, LIANGG J, LUOH B, et al. Attention assessment based on multi-view classroom behaviour recognition[J]. IET Computer Vision, 2025, 19(1): e12146. DOI:10.1049/cvi2.12146 .
[12]
WHITEHILLJ, SERPELLZ, LINY C, et al. The faces of engagement: Automatic recognition of student engagement from facial expressions[J]. IEEE Transactions on Affective Computing, 2014, 5(1):86-98. DOI: 10.1109/TAFFC.2014.2316163 .
[13]
KRITHIKAL B, LAKSHMI PRIYAGG. Student emotion recognition system (SERS) for e-learning improvement based on learner concentration metric[J]. Procedia Computer Science, 2016, 85: 767-776. DOI:10.1016/j.procs.2016.05.264 .
[14]
KARIMAHS N, HASEGAWAS. Automatic engagement estimation in smart education/learning settings: A systematic review of engagement definitions, datasets, and methods[J]. Smart Learning Environments, 2022, 9(1): 31. DOI:10.1186/s40561-022-00212-y .
[15]
ZALETELJJ, KOŠIRA. Predicting students’ attention in the classroom from Kinect facial and body features[J]. EURASIP Journal on Image and Video Processing, 2017, 2017(1): 80. DOI:10.1186/s13640-017-0228-8 .
JIAL Y, ZHANGZ H, ZHAOX Y, et al. Analysis of students status in class based on artificial intelligence and video processing[J]. Modern Educational Technology, 2019, 29 (12): 82-88. DOI: 10.3969/j.issn.1009-8097.2019.12.012(Ch ).
[18]
LIY T, QIX, SAUDAGARA K J, et al. Student behavior recognition for interaction detection in the classroom environment[J]. Image and Vision Computing, 2023, 136: 104726. DOI:10.1016/j.imavis.2023.104726 .
[19]
IKRAMS, AHMADH, MAHMOODN, et al. Recognition of student engagement state in a classroom environment using deep and efficient transfer learning algorithm[J]. Applied Sciences, 2023, 13(15): 8637. DOI: 10.3390/app13158637 .
[20]
XIONGY, GUOX Y, XUJ J. CNN-Transformer: A deep learning method for automatically identifying learning engagement[J]. Education and Information Technologies, 2024, 29(8): 9989-10008. DOI:10.1007/s10639-023-12058-z .
ZHANGQ, WUF T. Construction and empirical study of learning behavioral engagement evaluation framework[J]. China Educational Technology, 2018, (9): 102-108. DOI: 10.3969/j.issn.1006-9860.2018.09.015(Ch ).
[23]
CHIM T H. Active-constructive-interactive: A conceptual framework for differentiating learning activities[J]. Topics in Cognitive Science, 2009, 1(1): 73-105. DOI:10.1111/j.1756-8765.2008.01005.x .
[24]
CHIM T H, WYLIER. The ICAP framework: Linking cognitive engagement to active learning outcomes[J]. Educational Psychologist, 2014, 49(4): 219-243. DOI:10.1080/00461520.2014.965823 .
LENGJ, YIY H. The relationship between learning engagement and types of teaching activities in smart classroom[J]. Modern Educational Technology, 2020, 30(5): 47-53. DOI: 10.3969/j.issn.1009-8097.2020.05.007(Ch ).
[27]
EKMANP. An argument for basic emotions[J]. Cognition and Emotion, 1992, 6(3/4): 169-200. DOI:10.1080/02699939208411068 .
[28]
PEKRUNR, GOETZT, FRENZELA C, et al. Measuring emotions in students’ learning and performance: The achievement emotions questionnaire (AEQ)[J]. Contemporary Educational Psychology, 2011, 36(1): 36-48. DOI: 10.1016/j.cedpsych.2010.10.002 .
[29]
DANIELSL M, STUPNISKYR H, PEKRUNR, et al. A longitudinal analysis of achievement goals: From affective antecedents to emotional effects and achievement outcomes[J]. Journal of Educational Psychology, 2009, 101(4): 948-963. DOI: 10.1037/a0016096 .
[30]
PEKRUNR, ELLIOTA J, MAIERM A. Achievement goals and achievement emotions: Testing a model of their joint relations with academic performance[J]. Journal of Educational Psychology, 2009, 101(1): 115-135. DOI: 10.1037/a0013383 .
TANS Y, WANGZ X, HEG D. Real-time panoramic multi-scale classroom behaviors recognition based on CA-YOLOv9 network[J]. Modern Educational Technology, 2024, 34 (7): 123-130. DOI: 10.3969/j.issn.1009-8097.2024.07.013(Ch ).
[33]
CHEB L, LIX M, SUNY X, et al. A database of students’ spontaneous actions in the real classroom environment[J]. Computers and Electrical Engineering, 2022, 101: 108075. DOI: 10.1016/j.compeleceng.2022.108075 .
[34]
SIMONYANK, ZISSERMANA. Very deep convolutional networks for large-scale image recognition[EB/OL]. 2014: 1409.1556. DOI: 10.48550/arXiv.1409.1556 .
[35]
HEK M, ZHANGX Y, RENS Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE Press, 2016: 770-778. DOI:10.1109/CVPR.2016.90 .
[36]
SAURAVS, SAINIR, SINGHS. EmNet: A deep integrated convolutional neural network for facial emotion recognition in the wild[J]. Applied Intelligence, 2021, 51(8):5543-5570. DOI: 10.1007/s10489-020-02125-0 .