基于深度学习的学习情绪分析：方法与应用
DOI:
https://doi.org/10.70693/cjst.v1i1.852Keywords:
深度学习, 学习情绪, 多模态, 在线教育Abstract
学习情绪作为调节学习过程与成效的核心非认知因素，其精准识别与分析是落实《教育信息化2.0行动计划》中“发展智能教育”战略的关键突破口。本文基于深度学习技术构建面向教育场景的多维度情绪分析框架，重点解决教育情境特异性（如课堂/MOOC等）挑战。通过整合控制-价值情绪理论（Control-Value Theory）与多模态学习方法，建立包含文本语义特征（讨论区发言）、视觉行为特征（眼动/表情）及交互行为特征（点击流）的三维情绪表征体系。基于此构建的“情绪-认知-行为”动态干预模型，有效提升学习者课程完成率，缓解在线学习的高辍学率问题。
References
左秀媛,谭翔宇. 愉悦情绪、认知评价及行为投入对学术英语学习成效的影响[J]. 外语研究,2025,42(01):30-37.
俞建慧. 在线学习环境下基于交互视角的情绪分析及干预研究[D]. 浙江:浙江师范大学,2022.
Lei S, Dong G, Wang X, et al. InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models[J]. arXiv preprint arXiv:2309.11911, 2023.
Wu Z, Gong Z, Ai L, et al. Beyond silent letters: Amplifying llms in emotion recognition with vocal nuances[J]. arXiv preprint arXiv:2407.21315, 2024.
Pekrun R. Control-value theory: From achievement emotion to a general theory of human emotions[J]. Educational Psychology Review, 2024, 36(3): 83.
Lin H, Chen Q. Artificial intelligence (AI)-integrated educational applications and college students’ creativity and academic emotions: students and teachers’ perceptions and attitudes[J]. BMC psychology, 2024, 12(1): 487.
Linnenbrink-Garcia L, Pekrun R. Students’ emotions and academic engagement: Introduction to the special issue[J]. Contemporary educational psychology, 2011, 36(1): 1-3.
Liu Y, Ma S, Chen Y. The impacts of learning motivation, emotional engagement and psychological capital on academic performance in a blended learning university course[J]. Frontiers in Psychology, 2024, 15: 1357936.
Hasnine M N, Nguyen H T, Tran T T T, et al. A real-time learning analytics dashboard for automatic detection of online learners’ affective states[J]. Sensors, 2023, 23(9): 4243.
Liu S, Liu S, Liu Z, et al. Automated detection of emotional and cognitive engagement in MOOC discussions to predict learning achievement[J]. Computers & Education, 2022, 181: 104461.
Pekrun R. The control-value theory of achievement emotions: Assumptions, corollaries, and implications for educational research and practice[J]. Educational psychology review, 2006, 18: 315-341.
Pekrun R, Frenzel A C, Goetz T, et al. The control-value theory of achievement emotions: An integrative approach to emotions in education[M]//Emotion in education. Academic Press, 2007: 13-36.
Loderer K, Pekrun R, Lester J C. Beyond cold technology: A systematic review and meta-analysis on emotions in technology-based learning environments[J]. Learning and instruction, 2020, 70: 101162.
Pekrun R, Marsh H W, Elliot A J, et al. A three-dimensional taxonomy of achievement emotions[J]. Journal of Personality and Social Psychology, 2023, 124(1): 145.
Gan C, Zheng J, Zhu Q, et al. A survey of dialogic emotion analysis: Developments, approaches and perspectives[J]. Pattern Recognition, 2024: 110794.
Hu D, Wei L, Huai X. Dialoguecrn: Contextual reasoning networks for emotion recognition in conversations[J]. arXiv preprint arXiv:2106.01978, 2021.
Li W, Shao W, Ji S, et al. BiERU: Bidirectional emotional recurrent unit for conversational sentiment analysis[J]. Neurocomputing, 2022, 467: 73-82.
Wen J, Jiang D, Tu G, et al. Dynamic interactive multiview memory network for emotion recognition in conversation[J]. Information Fusion, 2023, 91: 123-133.
Ghosal D, Majumder N, Poria S, et al. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation[J]. arXiv preprint arXiv:1908.11540, 2019.
Ishiwatari T, Yasuda Y, Miyazaki T, et al. Relation-aware graph attention networks with relational position encodings for emotion recognition in conversations[C]. Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). 2020: 7360-7370.
Shen W, Wu S, Yang Y, et al. Directed acyclic graph network for conversational emotion recognition[J]. arXiv preprint arXiv:2105.12907, 2021.
Zhang Y, Jia A, Wang B, et al. M3GAT: A multi-modal, multi-task interactive graph attention network for conversational sentiment analysis and emotion recognition[J]. ACM Transactions on Information Systems, 2023, 42(1): 1-32.
Yang Z, Li X, Cheng Y, et al. Emotion recognition in conversation based on a dynamic complementary graph convolutional network[J]. IEEE Transactions on Affective Computing, 2024, 15(3): 1567-1579.
Zhong P, Wang D, Miao C. Knowledge-enriched transformer for emotion detection in textual conversations[J]. arXiv preprint arXiv:1909.10681, 2019.
Ghosal D, Majumder N, Gelbukh A, et al. Cosmic: Commonsense knowledge for emotion identification in conversations[J]. arXiv preprint arXiv:2010.02795, 2020.
Li Z, Tang F, Zhao M, et al. EmoCaps: Emotion capsule based model for conversational emotion recognition[J]. arXiv preprint arXiv:2203.13504, 2022.
Ma H, Wang J, Lin H, et al. A transformer-based model with self-distillation for multimodal emotion recognition in conversations[J]. IEEE Transactions on Multimedia, 2023.
Shen X, Huang X, Zou S, et al. Multimodal knowledge-enhanced interactive network with mixed contrastive learning for emotion recognition in conversation[J]. Neurocomputing, 2024, 582: 127550.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 朱颖雯, 张涛, 金鸽, 乔宇龙, 张迁
This work is licensed under a Creative Commons Attribution 4.0 International License.