ABSTRACT
Classroom interaction behavior research is an important part of classroom teaching quality evaluation, which can effectively improve teaching quality. Traditional classroom interaction behavior research is mainly carried out in the form of expert lectures and student questionnaires. This method can neither make the best use of the large amount of data generated in the classroom scene, nor can it provide an objective and detailed evaluation of the teaching quality. However, in the context of educational informatization, using information technology to observe and analyze classroom interaction can make full use of teaching data and provide timely and objective feedback on the teaching situation. This paper focuses on the analysis of classroom interaction behavior in colleges and universities. In order to make full use of classroom audio and video data, a framework for classroom interaction behavior analysis based on audio and video is constructed. It divides classroom interaction behaviors into verbal and non-verbal categories, and uses deep learning technology to realize automated classroom interaction analysis. The main work and innovations are as follows: (1) Combined with the theoretical basis of traditional classroom interaction analysis and the requirements of efficient classrooms for classroom quality evaluation, this paper constructs an audio-video-based classroom interaction behavior analysis framework. (2) The speaker segmentation and clustering algorithm in the verbal classroom interaction behavior analysis task is improved, and a frame feature extraction network integrating LSTM and TDNN and a temporal pooling network based on the dual multi-head attention mechanism are proposed. Compared with the DIHARD III baseline network, the improved speaker segmentation clustering algorithm reduces the speaker separation error rate (DER) by 3.24%, 3.19%, 4.53% and 4.14%, respectively, on the four types of evaluation datasets. (3) For the face detection algorithm in the non-verbal classroom interactive behavior analysis task, a single-stage face detection network FDN is proposed, and a bidirectional feature fusion module FPN+PANet, a prediction branch IoU- aware and a loss function CIoU are designed. Compared with RetinaFace, the final FDN has the most obvious improvement, and the average precision (Average Precision, AP) on the verification and test set difficult targets has increased by 2.6% and 2.7%, respectively.
- Guo Chunsheng, Zhang Xuguang, and Ying Na. Interactive Teaching Design and Practice in Information Theory Classroom. Modern Education, 44:066, 2019.Sam Anzaroot and Andrew McCallum. 2013. UMass Citation Field Extraction Dataset. Retrieved May 27, 2019 from http://www.iesl.cs.umass.edu/data/data-umasscitationfieldGoogle Scholar
- Tao Yibei. Construction of classroom teaching quality evaluation system based on big data. Science and Technology Vision, 31:124–125, 2021Google Scholar
- Fitri Mardiana, Zainuddin Zainuddin, and Johannes Jefria Gultom. Verbal interaction in English classroom using flanders interaction analysis categories system (fiacs). GENRE, 7(3):126–132, 2019.Google Scholar
- Cao Peijie. The triple realm of artificial intelligence education reform. Educational Research, 2:143–150, 2Google Scholar
- Sun Zhong, Lv Kaiyue, and Shi Zhiping. Testii framework: The development trend of AI-supported classroom teaching analysis. Research, 2:33–39, 2Google Scholar
- Zehui Zhan, Qianyi Wu, Zhihua Lin, and Jiayi Cai. Smart classroom environments affect teacher-student interaction: Evidence from a behavioural sequence analysis. Australasian Journal of Educational Technology, 37(2):96–109, 2021.Google ScholarCross Ref
- Jiaxin Lin, Jiamin Li, and Jie Chen. An analysis of english classroom behavior by intelli gent image recognition in iot. International Journal of System Assurance Engineering and Management, (1):1–9, 2021.Google Scholar
- Neville Ryant, Prachi Singh, Venkat Krishnamohan, Rajat Varma, Kenneth Church, Christo pher Cieri, Jun Du, Sriram Ganapathy, and Mark Liberman. The third dihard diarization challenge. arXiv preprint arXiv:2012.01477, 2020.Google Scholar
- Neville Ryant, Prachi Singh, Venkat Krishnamohan, Rajat Varma, Kenneth Church, Christo pher Cieri, Jun Du, Sriram Ganapathy, and Mark Liberman. The third dihard diarization challenge. arXiv preprint arXiv:2012.01477, 2020.Google Scholar
- Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, and Dongwei Ren. Distance iou loss: Faster and better learning for bounding box regression. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 12993–13000, 2020.Google ScholarCross Ref
- Jiankang Deng, Jia Guo, Evangelos Ververas, Irene Kotsia, and Stefanos Zafeiriou. Retinaface: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5203–5212, 2020.Google ScholarCross Ref
Index Terms
- Research on Classroom Interaction Behavior Analysis Algorithm based on Audio and Video
Recommendations
Dialogic teaching and iPads in the EAP classroom
Mobile learning technology in the form of iPads has gained considerable attention recently in the literature on pedagogy and learning. This has led to a change in the roles of teachers and students, and the nature of the classroom interaction. What is ...
Understanding Classroom Interaction Using Epistemic and Social Network Analysis
Blended Learning: Engaging Students in the New Normal EraAbstractThis study focuses on understanding classroom interaction using epistemic and social network analysis. Based on the classroom interaction data concerning an online course named Justice with 12 episodes, we demonstrate epistemic and social network ...
Exploring classroom interaction in online education
AbstractThis present study explores the nature and extent of classroom interaction in online English as a foreign language (EFL) classes at the university level. Based on an exploratory research design, the study involved the analysis of recordings of ...
Comments