| 438 | 0 | 115 |
| 下载次数 | 被引频次 | 阅读次数 |
在数字化学习背景下，智能感知成为理解与支持学习过程的关键路径。尽管多模态数据为社会调节学习开辟了新视角，其调节过程的复杂性仍带来语义对齐难、模态融合不充分以及识别精度受限等挑战。为此，本研究提出了融合语义定标、多模态特征对齐与多维时序建模的智能感知框架。该框架以言语主线划分语义片段，融合行为、生理与言语信号，构建感知特征矩阵并开展动态建模，实现对社会调节过程的自动识别。随后，本研究依托真实课堂中的多模态数据，开发了面向社会调节过程识别的人工智能模型。结果表明，模型识别性能稳定，验证了其在多模态数据驱动下的有效性。研究成果为复杂学习场景下社会调节的实时监测与智能支持提供了可推广的方法体系与实践基础。
Abstract：In the context of digital learning, intelligent perception has become a key approach to understanding and supporting learning processes. While multimodal data provides new perspectives for investigating socially regulated learning, the complexity of social regulation processes still presents major challenges for intelligent perception, including difficulties in semantic anchoring, insufficient modality fusion, and limited recognition accuracy. To address these challenges, this study proposes an intelligent perception framework that integrates semantic anchoring, multimodal feature alignment, and multi-dimensional temporal modeling. The framework segments verbal threads into semantic segments, integrates behavioral, physiological, and verbal signals to construct a perceptual feature matrix, and performs dynamic modeling to automatically identify social regulation processes. Based on real-world multimodal classroom data, an AI model is developed for social regulation recognition. Experimental results show that the model demonstrates stable recognition performance, confirming its effectiveness under multimodal data-driven conditions. This research provides a transferable methodological framework and practical foundation for real-time monitoring and intelligent support in complex learning environments.
[1]王一岩，郑永和.多模态数据融合：破解智能教育关键问题的核心驱动力[J].现代远程教育研究，2022(2):93-102.
[2]中华人民共和国教育部.教育部等九部门关于加快推进教育数字化的意见[EB/OL].[2025-07-03].http://www.moe.gov.cn/srcsite/A01/s7048/202504/t20250416_1187476.html.
[3]Su Y,Li Y,Hu H,et al.Exploring college English language learners’ self and social regulation of learning during wiki-supported collaborative reading activities[J].International Journal of Computer-Supported Collaborative Learning,2018(1):35-60.
[4]Volet S,Vauras M,Salonen P.Self-and social regulation in learning contexts:An integrative perspective[J].Educational Psychologist,2009(4):215-226.
[5]Pijeira-Díaz H J,Drachsler H,Kirschner PA,et al.Profiling sympathetic arousal in a physics course:How active are students?[J].Journal of Computer Assisted Learning,2018(4):397-408.
[6]Taub M,Azevedo R,Rajendran R,et al.How are students’ emotions related to the accuracy of cognitive and metacognitive processes during learning with an intelligent tutoring system?[J].Learning and Instruction,2021,72:101200.
[7]T?rm?nen T,J?rvenoja H,M?nty K.Exploring groups’ affective states during collaborative learning:what triggers activating affect on a group level?[J].Educational Technology Research and Development,2021(5):2523-2545.
[8]Sobocinski M,J?rvel? S,Malmberg J,et al.How does monitoring set the stage for adaptive regulation or maladaptive behavior in collaborative learning?[J].Metacognition and Learning,2020(2):99-127.
[9]刘清堂，李小娟，谢魁，等.多模态学习分析实证研究的发展与展望[J].电化教育研究，2022(1):71-78+85.
[10]赵春，舒杭，顾小清.基于计算机视觉技术的学生课堂学习行为投入度测量与分析[J].现代教育技术，2021(6):96-103.
[11]齐永锋，周晨阳.基于深度学习的学习者在线课堂参与度研究[J].现代教育技术，2021(12):42-50.
[12]Malmberg J,J?rvel? S,Holappa J,et al.Going beyond what is visible:What multichannel data can reveal about interaction in the context of collaborative learning?[J].Computers in Human Behavior,2019,96:235-245.
[13]T?rm?nen T,J?rvenoja H,M?nty K.All for one and one for all-How are students’ affective states and group-level emotion regulation interconnected in collaborative learning[J].International Journal of Educational Research,2021,109:101861.
[14]李月，姜强，赵蔚.基于过程挖掘的在线自主学习行为模式识别及干预实证研究[J].电化教育研究，2021(5):61-69.
[15]J?rvel? S,J?rvenoja H,Malmberg J,et al.Exploring socially shared regulation in the context of collaboration[J].Journal of Cognitive Education & Psychology,2013(3):267-286.
[16]Roschelle J,Teasley S D.The construction of shared knowledge in collaborative problem solving[C]// O’Malley C .Computer Supported Collaborative Learning.Berlin:Springer,1995:69-97.
[17]Khosa D K,Volet S E.Productive group engagement in cognitive activity and metacognitive regulation during collaborative learning:Can it explain differences in students’ conceptual understanding?[J].Metacognition and Learning,2014(3):287-307.
[18]徐晓青，赵蔚，刘红霞，等.学习分析对自我调节学习的影响机理研究[J].电化教育研究，2022(2):72-79.
[19]吴林静，高喻，涂凤娇，等.基于语义的在线协作会话学习投入自动分析模型及应用研究[J].电化教育研究，2022(3):77-84.
[20]Zabolotna K,Malmberg J,J?rvenoja H.Examining the interplay of knowledge construction and group-level regulation in a computer-supported collaborative learning physics task[J].Computers in Human Behavior,2023,138:107494.
[21]刘峰，刘雅旋，柴新宇，等.智能教育中可计算感知技术：系统性综述[J].计算机科学，2024(10):10-16.
[22]李佳泽，梅红岩，贾丽云，等.动态时间序列建模的多模态情感识别方法[J].计算机工程与应用，2025(1):196-205.
[23]黄春利，刘桂梅，姜文君，等.基于行为演化的学习模式识别及效果预测方法[J].计算机科学，2024(10):67-78.
[24]J?rvel? S,Nguyen A,Vuorenmaa E,et al.Predicting regulatory activities for socially shared regulation to optimize collaborative learning[J].Computers in Human Behavior,2023,144:107737.
[25]Nguyen A,J?rvel? S,Rosé C,et al.Examining socially shared regulation and shared physiological arousal events with multimodal learning analytics[J].British Journal of Educational Technology,2023(1):293-312.
[26]吴永和，郭胜男，朱丽娟，等.多模态学习融合分析(MLFA)研究：学理阐述、模型样态与应用路径[J].远程教育杂志，2021(3):32-41.
[27]J?rvel? S,Bannert M.Temporal and adaptive processes of regulated learning:what can multimodal data tell?[J].Learning and Instruction,2019,72:101268.
[28]Atkinson R C,Shiffrin R M.Human memory:A proposed system and its control processes[M]// Psychology of Learning and Motivation.Academic press,1968,2:89-195.
[29]Hadwin A F,J?rvel? S,Miller M.Self-regulation,co-regulation and shared regulation in collaborative learning environments[M]// Schunk D H,Greene J A.Handbook of Self-Regulation of Learning and Performance.2nd ed.New York:Routledge,2017:83-106.
[30]Dindar M,J?rvel? S,Nguyen A,et al.Detecting shared physiological arousal events in collaborative problem solving[J].Contemporary Educational Psychology,2022,69:102050.
[31]熊余，蔡婷，王盛松，等.融入学生认知迁移的教学评价情感分析[J].现代远距离教育，2024(3):68-76.
[32]徐亚萍，李艳燕，郭威彤，等.融合行为与情感分析的课堂学习投入智能评估[J/OL].武汉大学学报(理学版),1-13[2025-05-26].https://doi.org/10.14188/j.1671-8836.2024.0164.
[33]杨彦军，徐刚，童慧，等.智能学习环境中基于多模态数据的深度学习监测研究[J].电化教育研究，2022(6):68-76.
[34]Sobocinski M,Malmberg J,J?rvel? S.Exploring adaptation in socially-shared regulation of learning using video and heart rate data[J].Technology,Knowledge and Learning,2022(2):385-404.
[35]Bloom B S,Engelhart M D,Furst E J,et al.Taxonomy of educational objectives:the classification of educational goals;Handbook I:cognitive domain[M].New York:Longman,1956.
[36]Ouyang F,Xu W,Cukurova M,et al.An artificial intelligence-driven learning analytics method to examine the collaborative problem-solving process from the complex adaptive systems perspective[J].International Journal of Computer-Supported Collaborative Learning,2023(1):39-66.
[37]Malmberg J,Fincham O,Pijeira-Díaz H J,et al.Revealing the hidden structure of physiological states during metacognitive monitoring in collaborative learning[J].Journal of Computer Assisted Learning,2021(3):861-874.
[38]徐琦，魏艳涛，马玉建，等.基于视觉身心特征融合的学习投入识别研究[J].现代远距离教育，2025(2):68-78.
[39]吴军其，任飞翔，吴飞燕.数据驱动课堂精准施教关键指标体系构建及应用[J].现代远距离教育，2023(2):39-52.
[40]范福兰，李韩婷，戚天姣，等.基于多模态数据的大学生认知深度评价框架构建及应用[J].现代远距离教育，2023(3):57-65.
[41]余淑珍，单俊豪，闫寒冰.情感计算赋能个性化教学：逻辑框架、问题解构与多元重塑[J].现代远距离教育，2024(2):53-61.
基本信息:
DOI：10.13927/j.cnki.yuan.20251031.003
中图分类号:G434
引用信息:
[1]刘清堂,马思琪,马鑫倩,等.多模态数据驱动的社会调节过程智能感知及应用[J].现代远距离教育,2025,No.221(05):43-52.DOI:10.13927/j.cnki.yuan.20251031.003.
基金信息:
国家自然科学基金“融合多模态数据的信息化课堂教学交互行为识别及模式挖掘研究”(编号：62277021);国家自然科学基金项目“协作学习者社会认知调节过程的动态感知与精准干预研究”(项目编号：62577024);国家自然科学基金项目“数据驱动的在线学习协作会话过程监测与干预机制研究”(编号：72174070)