期刊文献+

一种改进的基于用户聚类的协同过滤算法 被引量:10

An Improved Collaborative Filtering Algorithm Based on User Clustering
收藏 分享 导出
摘要 协同过滤技术已经被成功地应用到个性化推荐系统中,但数据稀疏性问题严重影响着协同过滤算法的推荐质量。针对这一问题,本文引入用户兴趣的活跃度提出了一种改进的基于用户聚类的协同过滤算法,通过扩展用户—项目评分矩阵和改进用户相似性计算方法,缓解数据稀疏性对推荐算法的影响。实验结果表明,该算法能更准确地刻画用户之间的相似性,提高推荐算法的推荐准确度。 Collaborative filtering algorithms have been successfully applied to the network personalization recommendation system, but data sparseness affects the recommendation quality of collaborative filtering algorithms seriously. To solve this problem, this paper introduces the user activity and proposes an improved collaborative filtering algorithm based on user clustering. It extends user-item scoring matrix and improves user similarity computing method to alleviate the impact of data sparseness in recommendation algorithm. So it can significantly improve the accuracy of the collaborative recommendation algorithm. The experimental results show that it can describe the user similarity accurately and improve the accuracy of recommendation algorithm.
作者 张莉 秦桃 滕丕强 ZHANG Li, QIN Tao, TENG Pi-qiang (School of Information Technology & Management Engineering, University of International Business and Economics, Be(iing 100029,China)
出处 《情报科学》 CSSCI 北大核心 2014年第10期24-27,32共5页 Information Science
基金 国家社科基金项目(13BTQ027) 北京市哲学社会科学规划基金项目(12JGB034)
关键词 协同过滤 数据稀疏性 用户活跃度 用户兴趣 collaborative filtering data sparseness user activity user interesting
作者简介 张莉(1972-),女,山东人,副教授,博士,主要从事智能信息技术、数据挖掘、社会网络分析等研究.
  • 相关文献

参考文献14

  • 1张光前,雷彩华,吕晓敏.电子商务推荐的研究现状及其发展前景[J].情报杂志,2011,30(12):60-65. 被引量:13
  • 2FIDEL C.,V'CTOR C.,DIEGO F.& VREIXO O. Com- parison of Collaborative Fihering Algorithms: Limita- tions of Current Techniques and Proposals for Scal- able, High-Performance Recommender Systems[J]. ACM Transactions on the Web, 2011,5(1):2-33. 被引量:1
  • 3Xiaoyuan Su&Taghi M. K. A Survey of Collaborative Filtering Techniques[J]. Advances in Artificial Intelli- gence, 2009,(1):1-19. 被引量:1
  • 4李聪.电子商务协同过滤可扩展性研究综述[J].现代图书情报技术,2010(11):37-44. 被引量:9
  • 5Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. Rec- ommender systems for large-scale e-commerce: Scal- able neighborhood formation using clustering[C]. In Proceedings of the Fifth International Conference on Computer and Information Technology,2002. 被引量:1
  • 6G. Adomavicius & A. Tuzhilin. Toward the next gener- ation of recommender systems: A survey of the state-of-the-art and possible extensions[J]. IEEE Transactions On Knowledge And Data Engineering, 2005,17(6):734 - 749. 被引量:1
  • 7Rashid A M, Lain S K, Karyp is G, etal. ClustKNN: A Highly Scalable Hybrid Model & Memory-based CF Algorithm[C].In Proceedings of the KDD Workshop on Web Mining and Web Usage Analysis,2006. 被引量:1
  • 8Xue G, L in C, Yang Q, etal. Scalable Collaborative Filtering Using Cluster-based Smoothing[C]// In Pro- ceedings of the 28'h Annual International ACM SIGIR Conference on Research and Development in Informa- tion Retrieval. New York: ACM Press, 2005:114-121. 被引量:1
  • 9查文琴,梁昌勇,曹镭.基于用户聚类的协同过滤推荐方法[J].计算机技术与发展,2009,19(6):69-71. 被引量:15
  • 10Truong, K., Ishikawa, F., and Honiden, S. Improving accura- cy of recommender system by item clustering[J]. IEICE- Trans. Inf. Syst., 2007,E90-D(9):1363 - 1373. 被引量:1

二级参考文献71

共引文献489

同被引文献106

引证文献10

二级引证文献26

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈
新型冠状病毒肺炎防控与诊疗专栏