一种基于内容关联的学术资源协同推荐算法  

Academic resource collaborative recommendation algorithm based on content correlation

作　　者：周佳[1] 罗铁坚[1] 

机构地区：[1]中国科学院研究生院计算机与控制学院,北京100049

出　　处：《中国科学院研究生院学报》2013年第1期117-123,共7页Journal of the Graduate School of the Chinese Academy of Sciences

基　　金：国家自然科学基金(61103131)资助

摘　　要：利用学习者的关注点集中等特性,提出用网络日志推断学习意图、以内容关联匹配兴趣主题的理论框架和相应的协同推荐算法.实验表明,算法的覆盖率与经典方法无显著性差异,准确率提高5.13%,响应时间缩减为1/9,并在训练测试比小于50%时准确率提高6.73%.We propose an academic resource collaborative recommendation algorithm by analyzing Web log to find learner＇ s intention and mining content correlation to match interest. Experiments show that there is no significant difference in coverage between our algorithm and the existing method. The accuracy is improved by 5.13% and the response time reduces to 1/9. The accuracy is improved by 6.73% when the training/test ratio is less than 50%.

关 键 词：学术资源推荐 协同过滤 内容关联 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]