摘要
为了解决给规模大、分布广的远程学习者提供个性化的学习资源推荐的这一难点问题,提出了一种新颖的基于多代理的远程协作学习资源推荐机制,引入学习状态评估向量对复杂的学习行为进行建模,并基于组代理之间的交互来发现具有相似学习状态的学习者,同时构建了一个供社区学习者共享的即时交互和学习资源推荐平台,为社区学习者的学习资源共享提供了有针对性的推荐.实验证明,具有较高的相似学生发现准确率和社区构建效率,同时通过社区学生的资源推荐和共享,提高了学习者的学习效率和成绩.
A novel E-learning resource collaborative recommendation mechanism based on multi-agent was proposed to solve the big challenge to provide personalized learning resource to large-scale and distributed E-learners. A learning status evaluation vector was introduced to model the E-learners＇ behaviors, and help to find and reorganize the learners＇ share of similar learning status into smaller communities based on the interaction between group agents. Furthermore a collaborative communication and learning resource recommendation platform was developed to enable the learner to share personalized recommended resources. Experimental results showed that this algorithm has higher discovery accuracy of similar E-learner .and construction efficiency of community. Based on the learning resource recommendation and sharing among E-learners in the common community, this system is proved to enhance the learning effect and scores.
出处
《浙江大学学报（工学版）》
EI
CAS
CSCD
北大核心
2006年第10期1688-1691,1791,共5页
Journal of Zhejiang University：Engineering Science
基金
国家自然科学基金资助项目(60372078)
关键词
远程教育
资源过滤
推荐系统
学习社区
E-learning
resource fihering
recommendation system
learning communities
