【作 者】：
郑兰琴， 范云超， 牛佳玉
【关 键 词 】：
在线协作学习； 知识图谱； 跨领域； 在线交互文本； 知识建构
【栏 目】：
网络教育
【中文摘要】：
在线协作学习已经成为教育领域广泛采用的学习方式。然而，在线协作学习过程中学习者会产生海量的交互文本。人工分析在线交互文本不仅费时费力，而且难以为学习者提供实时、个性化的反馈。为解决这一问题，研究提出了基于在线协作学习交互文本的跨领域知识图谱构建技术，该技术包括实体识别、关系抽取和领域知识图谱生成技术。研究还对自动构建的知识图谱在不同的领域进行了检验和应用。结果表明，研究提出的跨领域知识图谱构建技术路线可行有效，学习者普遍受益。自动构建的领域知识图谱不仅为学习者提供直观、可视化、实时的反馈，而且能够促进学习者进行协同知识建构和社会性调节。教师也能根据自动构建的领域知识图谱为学习者提供个性化的学习支持服务。
【英文摘要】：
Online collaborative learning has been widely adopted in the field of education. However, a huge amount of interactive texts have been generated by learners during online collaborative learning. Manual analysis of online interactive texts is not only time-consuming and laborious, but also difficult to provide real-time and personalized feedback to learners. To solve this problem, this study proposes a cross-domain knowledge graph construction technology based on interactive texts of online collaborative learning, which includes entity recognition, relationship extraction, and knowledge graph generation. This study also tests and applies the automatically constructed knowledge graphs in different domains. The results indicate that the technical route of cross-domain knowledge graph construction proposed in this study is feasible and effective, and the learners generally benefit a lot. The automatically constructed domain knowledge graphs can not only provide intuitive, visual, and real-time feedback for learners, but also promote collaborative knowledge building as well as social regulation. Teachers can also provide personalized learning support services for learners based on the automatically constructed domain knowledge graphs.