Application and Effectiveness Evaluation of Deep Learning-Based Multimodal Sentiment Analysis in Ideological and Political Classrooms
Main Article Content
Abstract
In ideological and political classrooms, teachers often struggle to identify students’ emotional states accurately and adjust teaching strategies in time, which can reduce teaching effectiveness. This study proposes a deep-learning-based multimodal sentiment analysis method for classroom application. A multimodal acquisition system collects facial expression, speech intonation, and text semantic data from 320 students across 36 class sessions. A parallel neural architecture combining ResNet, BiLSTM, CNN-LSTM, BERT, and an attention-based fusion mechanism is constructed to extract and integrate visual, audio, and textual features. Transfer learning, data augmentation, and focal loss are used to improve model robustness, while an edge-computing architecture protects privacy by processing biometric data locally. Experimental results show that the proposed multimodal attention model achieves 92.7% accuracy, outperforming the best single-modal and bimodal models. In teaching application, classroom participation increases by 28.6%, knowledge acquisition by 21.4%, and satisfaction from 67.3% to 89.8%. The system supports intelligent teaching and is compatible with wireless classroom sensing and electromagnetic-safe data acquisition environments.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
H. Xu, “Multimodal Sentiment Analysis,” Multi-Modal Sentiment Analysis, pp. 217-240, 2023, doi: 10.1007/978-981-99-5776-7_6.
T. Zhou, “Sentiment-aware multimodal pre-training for multimodal sentiment analysis,” Knowledge-Based Systems, vol. 258, 2022, doi: 10.1016/j.knosys.2022.110021.
B. Ellison, E. Marwood, and H. Sinclair, “Multimodal Fusion Network for Multimodal Sentiment Analysis,” 2025, doi: 10.20944/preprints202502.1769.v1.
T. Kim and B. Lee, “Multi-Attention Multimodal Sentiment Analysis,” Hyundai Robotics, Yongin, South Korea; Inha University, Incheon, South Korea, 2020, doi: 10.1145/3372278.3390698.
K. Zhu, C. Fan, J. Tao, et al., “Prompt Link Multimodal Fusion in Multimodal Sentiment Analysis,” Interspeech 2024, pp. 4668-4672, 2024, doi: 10.21437/interspeech.2024-1512.
S. Zhang, Y. He, L. Li, et al., “Multimodal sentiment analysis with BERT-ResNet50,” Proceedings of SPIE, 2023, doi: 10.1117/12.2679113.
Z. Tang, “Review of Multimodal Sentiment Analysis Techniques,” Applied and Computational Engineering, vol. 120, no. 1, pp. 88-97, 2024, doi: 10.54254/2755-2721/2025.18747.
J. Wu, T. Zhu, J. Zhu, et al., “A Optimized BERT for Multimodal Sentiment Analysis,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), vol. 19, no. 2-Sup, Art. no. 12, 2023, doi: 10.1145/3566126.
H. Xu, W. Li, D. Takabi, et al., “Privacy-Preserving Multimodal Sentiment Analysis,” IEEE Internet of Things Journal, pp. 1-1, 2025, doi: 10.1109/jiot.2025.3527864.
B. Ren, T. Cao, Z. Zhang, et al., “Hierarchical Signal Calibration and Refinement for Multimodal Sentiment Analysis,” IEEE Signal Processing Letters, vol. 32, no. 32, pp. 3450-3454, 2025, doi: 10.1109/LSP.2025.3603884.