融合奇异值分解和动态转移链的学术资源推荐模型(英文)  

A novel academic recommendation model with singular value decomposition and dynamic transfer chain

作　　者：罗铁坚[1] 程福兴[1] 周佳[1] 

机构地区：[1]中国科学院大学信息科学与工程学院,北京100049

出　　处：《中国科学院大学学报（中英文）》2014年第2期257-266,共10页Journal of University of Chinese Academy of Sciences

基　　金：Supported by National Natural Science Foundation of China(61103131/F020511)

摘　　要：学术资源推荐领域学习者兴趣和学术趋势随时间的变化影响学术资源推荐系统的准确性.现有大部分推荐方法都没有考虑时间因素.本文用动态转移链(DTC)对用户兴趣和学术趋势的时效性进行建模.在DTC框架的基础上,提出一种新的融合矩阵奇异值分解模型(SVD)和动态转移链的学术资源推荐算法(SVD&DTC).在数据集SeekSearch上对该方法进行实验,结果表明该算法较之当前流行的主要算法准确率提升3.89%.In the field of academic recommendation, changes in learner＇s preferences and academic trends with time affect the accuracy of academic recommendation systems. Most of the existing recommendation methods do not consider the time factor. We propose the dynamic transfer chain （DTC） to model users＇ preferences and academic trends over time. Based on DTC framework, we present a novel temporal academic recommendation algorithm （SVD＆DTC） which combines singular value decomposition （SVD） and DTC together. Finally, we evaluate the effectiveness of the method using datasets on SeekSearch, and the results show a 3.89% improvement over the previous start-of- the -art.

关 键 词：学术资源推荐 动态转移链 奇异值分解 时效性推荐 

分 类 号：O153[理学—数学]