首页> 外文会议>International symposium on IT in medicine and education >Chapter 50 A Knowledge-Based Teaching Resources Recommend Model for Primary and Secondary School Oriented Distance-Education Teaching Platform
【24h】

Chapter 50 A Knowledge-Based Teaching Resources Recommend Model for Primary and Secondary School Oriented Distance-Education Teaching Platform

机译:第五十章中小学远程教育教学平台的知识型教学资源推荐模型

获取原文

摘要

In distance education systems, the ranked list of resources is very important for learners and teachers to find useful resources effectively. Apart from user's interest, the knowledge point of subject is a crucial factor for education system, especially for primary and secondary school oriented distance education. Much of the previous work are models based on recommender systems, however, these models considered only user's interest, ignoring the crucial impact of subject knowledge. In order to improve the performance of recommender systems, we considered both the subject knowledge and user's interest. To get this target, Latent Knowledge Model (LKM) is adopted. LKM is a knowledge-based and teaching task-oriented model. It enables subject knowledge resources through knowledge tree extended search strategy, and gets personalized resources through user feature mining strategy. LKM is realized on real data sets which are obtained from a popular distance education teaching platform. Recall and precision rate are used to evaluate the performance of our proposed method for resources recommendation tasks. Experimental results show that the LKM captures subject knowledge and personal preferences for resources selection, which yields significant improvement in recommendation accuracy.
机译:在远程教育系统中,资源的排序列表对于学习者和教师有效地找到有用的资源非常重要。除了用户的兴趣外,学科的知识点是教育体系的一个关键因素,特别是对于面向中小学的远程教育。先前的许多工作都是基于推荐系统的模型,但是,这些模型仅考虑用户的兴趣,而忽略了主题知识的关键影响。为了提高推荐系统的性能,我们同时考虑了主题知识和用户兴趣。为了达到这个目标,采用了潜在知识模型(LKM)。 LKM是一个基于知识和教学任务导向的模型。它通过知识树扩展的搜索策略来启用主题知识资源,并通过用户特征挖掘策略来获取个性化资源。 LKM是在从流行的远程教育教学平台获得的真实数据集上实现的。召回率和准确率用于评估我们提出的资源推荐任务方法的性能。实验结果表明,LKM可以捕获主题知识和个人偏好以进行资源选择,从而显着提高推荐准确性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号