[1]丁继红,罗 寒,刘华中,等.融合专家分类与情境语义标注的学习资源表征方法[J].远程教育杂志,2019,(03):078-85.[doi:10.15881/j.cnki.cn33-1304/g4.2019.03.008]
 Ding Jihong,Luo Han,Liu Huazhong,et al.A Fusion Representation Method of Learning Resources based on Expert Classification and Situational Semantic Annotations[J].Distance Education Journal,2019,(03):078-85.[doi:10.15881/j.cnki.cn33-1304/g4.2019.03.008]
点击复制

融合专家分类与情境语义标注的学习资源表征方法()
分享到:

《远程教育杂志》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年03期
页码:
078-85
栏目:
学习新论
出版日期:
2019-05-15

文章信息/Info

Title:
A Fusion Representation Method of Learning Resources based on Expert Classification and Situational Semantic Annotations
作者:
丁继红; 罗 寒; 刘华中; 王永固
1.浙江工业大学 教育科学与技术学院,浙江杭州 310023;2.九江学院 信息科学与技术学院,江西九江 332005
Author(s):
Ding Jihong; Luo Han; Liu Huazhong; Wang Yonggu
1.School of educational science and technology, Zhejiang University of Technology, Hangzhou, Zhejiang 310023 2.School of Information Science and Technology, Jiujiang University, Jiujiang, Jiangxi 332005
关键词:
学习资源表征情境语义标注智能学习资源聚合
Keywords:
Learning Resource Representation Situational Semantic Annotation Smart Learning Resource Aggregation
分类号:
G420
DOI:
10.15881/j.cnki.cn33-1304/g4.2019.03.008
文献标志码:
A
摘要:
学习资源特征属性的全面提取与准确表征是在智能学习环境下提供个性化、情境式学习服务的前提。有效、规范的学习资源表征方法能涵盖资源的内容特性,标识其适用情境,支持语义关联、内容聚合和情景推荐,适应情境化和协作性的学习需求。构建自上而下的专家分类与自底向上的情境语义协同标注的学习资源表征方式,有利于学习资源特征的准确提取和关系聚合。具体而言,要实现对学习资源特征多视角、多层次的揭示和表征,需要在剖析不同学习资源表征方式的特征基础上,以专家分类元数据为框架,结合用户情境语义协同标注的学习资源表征方式,引入社会网络分析方法梳理、重构学习资源特征的语义关系和层次结构,形成自上而下的专家分类与自底向上的情境语义协同标注的学习资源表征方式,达到用户协同和情境融合。实验研究也验证了该方法的有效性。这为探索融合专家、用户多视角对学习资源的内容特征和情境内涵表征提供了新思路。
Abstract:
The comprehensive extraction and accurate representation of the features of learning resources is the premise of providing personalized and situated learning services in an intelligent learning environment. An effective and standardized representation method of learning resources should cover the content characteristics and application situation of resources, and support semantic association, content aggregation and situated recommendation, thus adapt to situated and collaborative learning. The representation of learning resources based on top-down expert classification and bottom-up situated semantic collaborative annotation is proposed, which makes it possible to accurately extract and aggregate the features of learning resources. Specifically, in order to reveal and represent the features of learning resources from multiple perspectives and levels, the characteristics of different existing resource description models are firstly analyzed in depth, and the expert classification metadata is defined as the framework, combining with social annotation, and the social network analysis method is also employed to analyze the semantic relations and reconstruct the layers of learning resources’ features. By this way, a top-down expert classification and bottom-up context semantic collaborative annotation is proposed to represent learning resources characterized by users collaboration and context fusion. In addition, the experimental study also verifies the effectiveness of this method. The research provides a new approach to representing the content and contextual features of learning resources from the experts’ and users’ perspective.

备注/Memo

备注/Memo:
基金项目:本文系国家自然科学基金项目“基于多维关联分析的教育精准服务模式研究”(71704160)、国家自然科学基金项目“高维空间下大数据多模态聚类与预测及精准教育服务研究”(61867002)和浙江省教育科学规划课题“‘异地同步网络教研’的环境构建、模式创新及绩效评价研究”(2017SCG256)的研究成果之一。
更新日期/Last Update: 1900-01-01