Linked Open Data-Driven Contrastive Cognitive Subgraph Searching for Understanding Concepts in e-Learning
2018 IEEE 15th International Conference on e-Business Engineering (ICEBE)(2018)
摘要
Along with rise of e-learning, searching services as an important part of e-learning system has attracted more and more e-learners and researchers. According to theory of cognitive development, when e-learners are having problems to understand a concept during online learning, they prefer to search related information to form new cognitive structures or strengthen existing cognitive structures in order to improve learning efficiency. Although the existing search engines are extremely mature, they play a less role in cognitive structures for e-learners. Depending on the theory of constructivism, an effective mean to improve cognitive efficiency is to enhance the improvement and development of individual cognitive structure. Therefore, relying on thinking map, we develop a Linked Open Data-driven contrastive cognitive subgraph searching system for understanding concepts. Besides, during constructing contrastive cognitive subgraphs, we propose a method of calculating similarity between two keywords, whose accuracy and stability have been effectively improved compared with the other algorithm on LOD.
更多查看译文
关键词
linked open data,cognitive subgraph,similarity calculation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络