ACC
Construction and Empirical Study of Intelligent Recognition and Analysis Model of Multimodal Classroom Behavior
TOTAL VIEWS: 441
Abstract
Under the empowerment of emerging technologies, smart classrooms provide rich educational multimodal data for monitoring, evaluating, providing feedback, and warning students about learning behaviors. Fully collecting, processing, and analyzing educational multimodal data can serve as a reference for educational research and practice. Firstly, by reviewing existing studies on smart classroom learning behavior analysis and multimodal data teaching research, drawing on the learning behavior classification system, a three-dimensional multimodal data analysis framework based on multimodal data types—audio data, image data, and text data—is constructed to present changes in students learning behaviors from four aspects: verbal learning activities, positional movements, bodily actions, and technology usage. Secondly, multimodal data representing students' learning behavior characteristics are encoded and qualitatively characterized to form an encoding system. Lastly, from the perspective of situational and temporal behavior analysis, frequency changes and periodic changes in learning behavior multimodal data from lesson examples are analyzed. The study concludes that under the smart classroom environment, students' participation, initiative, and focus in class learning are continuously improving, the classroom learning atmosphere is developing positively, and ineffective and irrelevant learning behaviors are gradually decreasing. Additionally, by analyzing the multimodal data of students learning behaviors, it aims to help students understand their own learning behaviors and states, and enable teachers to conduct personalized teaching. In addition, researchers construct a learning evaluation system to provide data sources and scientific basis.
References
[1] Álvarez IM, Manero B, Romero-Hernández A, Cárdenas M, Masó I. Virtual reality platform for teacher training on classroom climate management: Evaluating user acceptance. Virtual Reality. 2024.
[2] Moore TC, Daniels S, Taylor KLH, Oliver RM, Chow J, Wehby JH. Supporting teachers’ effective classroom and behavior management: What do teachers tell us? Preventing School Failure: Alternative Education for Children and Youth. 2024.
[3] Herman KC, Reinke WM, Dong N, Bradshaw CP. Can effective classroom behavior management increase student achievement in middle school? Findings from a group randomized trial. Journal of Educational Psychology. 2022.
[4] Lohmann MJ, Randolph KM, Oh JH. Classroom management strategies for Hyflex instruction: Setting students up for success in the hybrid environment. Early Childhood Education Journal. 2021.
[5] Chen T, Mei X. Empirical study on user portrait identification and recommendation of multi-source data fusion. Information Theory and Practice. 2024;47(04):171-180.
doi:10.16353/j.cnki.1000-7490.2024.04.022.
[6] Fang H, Hong X, Shu L, et al. Research on teachers' teaching ability analysis framework and its application based on classroom intelligence analysis model. Modern Educational Technology. 2024;34(02):43-52. doi:10.3969/j.issn.1009-8097.2024.02.005.
[7] Gao D, Wu H, Li Z. Construction and empirical research on patent information. Scientific and Technological Intelligence Research. 2024;6(03):69-82.
doi:10.19809/j.cnki.kjqbyj.2024.03.006.
[8] Shenzhen University. A behavior recognition system and recognition method for a multi-mode sensor: CN110807471B [Patent]. 2024-02-02 [cited 2024-12-21]. Available from: https://www.cqvip.com/doc/patent/3338840999.
[9] Shen Y, Huang W. Research and application of grid governance work order generation based on multimodal large model. Jiangsu Communications. 2024;40(01):87-91+96.
[10] Yin B, Wang X, Sun X, et al. Multimodal decoding of teacher classroom management behavior: Behavioral characteristics, classification identification, and timing development. Electrochemical Education Research. 2024;45(10):101-109.
doi:10.13811/j.cnki.eer.2024.10.014.
[11] Tang Q, Zhang H, Wu Y. Construction of a multimodal learning analysis model in the intelligent classroom. Journal of Teacher Education. 2024;11(05):49-58.
doi:10.13718/j.cnki.jsjy.2024.05.006.
How to cite this paper
Construction and Empirical Study of Intelligent Recognition and Analysis Model of Multimodal Classroom Behavior
How to cite this paper: Tong Su. (2025) Construction and Empirical Study of Intelligent Recognition and Analysis Model of Multimodal Classroom Behavior. Advances in Computer and Communication, 6(1), 20-26.
DOI: http://dx.doi.org/10.26855/acc.2025.01.004
More Articles
- Improvement of a Human Pose Estimation Strategy
- Sentiment Analysis on YouTube Data: A Comparison of TextBlob and VADER
- Prediction of Student Performance Based on MPL
- Construction and Empirical Study of Intelligent Recognition and Analysis Model of Multimodal Classroom Behavior
- Application of Graph Alignment Double Layer Attention Mechanism in Detecting Malicious Traffic in TLS/SSL Encryption
- Study on Computer Fuzzy Comprehensive Evaluation and Correlation Analysis—Taking the Study on the Best Habitat of Antarctic Krill as an Example