支持个性化学习的行为大数据可视化研究
|
摘要
学习云空间是基于云计算技术构建的网络化学习空间,是重要的在线学习环境。空间中行为大数据的直观展示,对学习智能监测与适应性调整至关重要。本研究旨在探讨如何通过动态可视化呈现学习者在云空间中的行为关联大数据,为个性化知识建构提供及时反馈、监督与指导。研究先基于领域特征需求和可视化支撑技术,提出适用于云空间学习环境的可视化设计原则,建立面向智能学习服务的行为大数据可视化机制;然后结合不同空间学习形式,分析可视化内容、方式与时机的判定理论;再针对典型学习场景,制定个性化云空间可视化元素的适应性变更、基于学习全过程的知识点动态组织、交互感知下的可视化方式即时转换和面向群组角色的差异化内容呈现等可视化实现策略;最后采用问卷调查法和实验研究法分析可视化应用的实践效果。结果表明,本研究提出的可视化方案对网络学习空间的个性化学习活动推进及效果提升有良好的支持作用。
Personalized learning has become an indispensable part of instructional reform, and the application of big data technology provides a new approach to its implementation. Cloud-based learning space, constructed by cloud computing technology, is an important online learning environment. The visualization of behavioral big data is crucial to intelligently monitor and adaptively adjust learning process for satisfying the personalized knowledge construction. Therefore, the purpose of this paper is to explore how to dynamically visualize big data related to learners' behaviors in the cloud-based learning space, so as to provide timely feedback, supervision, guidance for personalized knowledge construction. According to the characteristics of cloud-based learning space, principles of visualization design are proposed,which are based on the specific domain requirements and visual support technologies. Subsequently, the visualization mechanism is established in terms of intelligent learning services. Furthermore, visualization contents, visualization methods and visualization time are specifically probed by taking into account different learning ways. In addition, four implementation strategies are formulated for typical learning scenarios, including the personalized adaptive change of visualization elements, the dynamic organization of knowledge points throughout the learning process, the immediate transformation of visualization method under interactive perception and the differentiated content presentation for different group roles. Finally, the methods of questionnaire design and comparative experiment are conducted to analyze the practical effect. The results show that the proposed visualization scheme has a strong support for personalized learning activities and the improvement of learning effect.
Personalized learning has become an indispensable part of instructional reform, and the application of big data technology provides a new approach to its implementation. Cloud-based learning space, constructed by cloud computing technology, is an important online learning environment. The visualization of behavioral big data is crucial to intelligently monitor and adaptively adjust learning process for satisfying the personalized knowledge construction. Therefore, the purpose of this paper is to explore how to dynamically visualize big data related to learners' behaviors in the cloud-based learning space, so as to provide timely feedback, supervision, guidance for personalized knowledge construction. According to the characteristics of cloud-based learning space, principles of visualization design are proposed,which are based on the specific domain requirements and visual support technologies. Subsequently, the visualization mechanism is established in terms of intelligent learning services. Furthermore, visualization contents, visualization methods and visualization time are specifically probed by taking into account different learning ways. In addition, four implementation strategies are formulated for typical learning scenarios, including the personalized adaptive change of visualization elements, the dynamic organization of knowledge points throughout the learning process, the immediate transformation of visualization method under interactive perception and the differentiated content presentation for different group roles. Finally, the methods of questionnaire design and comparative experiment are conducted to analyze the practical effect. The results show that the proposed visualization scheme has a strong support for personalized learning activities and the improvement of learning effect.
引文
[1]Bakharia, A., & Dawson, S.(2011). SNAPP: A bird's-eye view of temporal participant interaction[A]. Proceedings of the 1st International Conference on Learning Analytics and Knowledge[C]. ACM: 168-173.
[2]陈为,沈则潜,陶煜波(2013).数据可视化[M]. 北京:电子工业出版社:4.
[3]郭绍青,贺相春,张进良,李玉斌(2017).关键技术驱动的信息技术交叉融合:网络学习空间内涵与学校教育发展研究之一[J]. 电化教育研究,(5):28-35.
[4]黄安心(2015).开放学习资源设计、开发与运营的可视化策略[J]. 中国电化教育,(7):66-72.
[5]黄昌勤,王希哲,张冬冬,梅晓勇,周宇文(2015a).学习云空间支持下的研究性学习研究与实践[J]. 中国电化教育,(8):21-28.
[6]黄昌勤,王希哲,罗旋,张冬冬(2015b).iStudy学习云空间软件系统[P]. 中国:2015SR068805.
[7]Leony, D., Pardo, A.,& Kloos, C. D. (2012). GLASS:A learning analytics visualization tool[A]. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge [C]. ACM: 162-163.
[8]Mackay, R. F.(2013). Learning analytics at Stanford takes huge leap forward with MOOCs[EB/OL]. [2018-03-13]. https://news.stanford.edu/news/2013/april/online-learning-analytics-041113.html.
[9]Martin, T., Aghababyan, A., Pfaffman, J., Olsen, J., Baker, S.,& Janisiewicz, P.(2013). Nanogenetic learning analytics: Illuminating student learning pathways in an online fraction game[A]. Proceedings of the 3rd International Conference on Learning Analytics and Knowledge[C]. ACM: 165-169.
[10]Paivio, A.(1986). Mental representations: A dual coding approach[M].New York: Oxford University Press:53.
[11]Pardo, A., Mirriahi, N., Dawson, S., Zhao, Y.,& Zhao, A.(2015). Identifying learning strategies associated with active use of video annotation software[A]. Proceedings of the 15th International Conference on Learning Analytics And Knowledge[C]. ACM: 255-259.
[12]Ruipérez-Valiente, J. A., Muňoz-Merino, P. J., Leony, D.,& Kloos, C. D.(2015). Alas-ka: A learning analytics extension for better understanding the learning process in the khan academy platform[J]. Computers in Human Behavior, (47): 139-148.
[13]Ward, M., Grinstein, G.,& Keim, D.(2010). Interactive data visualization: Foundations, techniques, and applications[M]. Florida : CRC Press: 36.
[14]杨现民,程罡,余胜泉(2013).学习元平台的设计及其应用场景分析[J]. 电化教育研究,34(3):55-61.
[15]杨现民,赵鑫硕,刘雅馨,潘青青,陈世超(2016).网络学习空间的发展:内涵、阶段与建议[J]. 中国电化教育,(4):30-36.
[16]张洪孟,胡凡刚(2015).教育虚拟社区:教育大数据的必然回归[J]. 开放教育研究,21(1):44-52.
[2]陈为,沈则潜,陶煜波(2013).数据可视化[M]. 北京:电子工业出版社:4.
[3]郭绍青,贺相春,张进良,李玉斌(2017).关键技术驱动的信息技术交叉融合:网络学习空间内涵与学校教育发展研究之一[J]. 电化教育研究,(5):28-35.
[4]黄安心(2015).开放学习资源设计、开发与运营的可视化策略[J]. 中国电化教育,(7):66-72.
[5]黄昌勤,王希哲,张冬冬,梅晓勇,周宇文(2015a).学习云空间支持下的研究性学习研究与实践[J]. 中国电化教育,(8):21-28.
[6]黄昌勤,王希哲,罗旋,张冬冬(2015b).iStudy学习云空间软件系统[P]. 中国:2015SR068805.
[7]Leony, D., Pardo, A.,& Kloos, C. D. (2012). GLASS:A learning analytics visualization tool[A]. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge [C]. ACM: 162-163.
[8]Mackay, R. F.(2013). Learning analytics at Stanford takes huge leap forward with MOOCs[EB/OL]. [2018-03-13]. https://news.stanford.edu/news/2013/april/online-learning-analytics-041113.html.
[9]Martin, T., Aghababyan, A., Pfaffman, J., Olsen, J., Baker, S.,& Janisiewicz, P.(2013). Nanogenetic learning analytics: Illuminating student learning pathways in an online fraction game[A]. Proceedings of the 3rd International Conference on Learning Analytics and Knowledge[C]. ACM: 165-169.
[10]Paivio, A.(1986). Mental representations: A dual coding approach[M].New York: Oxford University Press:53.
[11]Pardo, A., Mirriahi, N., Dawson, S., Zhao, Y.,& Zhao, A.(2015). Identifying learning strategies associated with active use of video annotation software[A]. Proceedings of the 15th International Conference on Learning Analytics And Knowledge[C]. ACM: 255-259.
[12]Ruipérez-Valiente, J. A., Muňoz-Merino, P. J., Leony, D.,& Kloos, C. D.(2015). Alas-ka: A learning analytics extension for better understanding the learning process in the khan academy platform[J]. Computers in Human Behavior, (47): 139-148.
[13]Ward, M., Grinstein, G.,& Keim, D.(2010). Interactive data visualization: Foundations, techniques, and applications[M]. Florida : CRC Press: 36.
[14]杨现民,程罡,余胜泉(2013).学习元平台的设计及其应用场景分析[J]. 电化教育研究,34(3):55-61.
[15]杨现民,赵鑫硕,刘雅馨,潘青青,陈世超(2016).网络学习空间的发展:内涵、阶段与建议[J]. 中国电化教育,(4):30-36.
[16]张洪孟,胡凡刚(2015).教育虚拟社区:教育大数据的必然回归[J]. 开放教育研究,21(1):44-52.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |