计算机科学 ›› 2015, Vol. 42 ›› Issue (3): 252-255.doi: 10.11896/j.issn.1002-137X.2015.03.052

• 人工智能 • 上一篇    下一篇

基于动态社会行为和用户背景的协同推荐方法

蒋 胜,王忠群,修 宇,皇苏斌,汪千松   

  1. 安徽工程大学计算机与信息学院 芜湖241000,安徽工程大学计算机与信息学院 芜湖241000,安徽工程大学计算机与信息学院 芜湖241000,安徽工程大学计算机与信息学院 芜湖241000,安徽工程大学计算机与信息学院 芜湖241000
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(71371012,2,61300170),教育部人文社科规划项目(13YJA630098)资助

Collaborative Filtering Recommendation Method Based on Dynamic Social Behavior and Users’ Background Information

JIANG Sheng, WANG Zhong-qun, XIU Yu, HUANG Su-bing and WANG Qian-song   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对传统协同过滤推荐算法推荐精度低及冷启动的问题,提出了一种基于动态社会行为和用户背景的协同推荐方法。作为用户标注行为的结果,变化的标签体现了用户行为的动态性。该方法首先根据动态社会化标签得出用户的动态兴趣偏好相似度,然后根据用户背景信息计算出用户相似度,最后计算基于时间权重的用户评分相似度,并集成上述3个相似度找出最近邻居集,以为目标用户提供更加准确的个性化推荐。实验结果证明,该方法不仅能较好地解决数据稀疏和冷启动的问题,还能有效提高推荐算法的精确度。

关键词: 推荐精度,冷启动,社会化标签,用户背景信息,动态社会行为,时间权重

Abstract: To address the difficulty of data sparsity and lower recommendation precision in the traditional collaborative filtering recommendation algorithm,a new collaborative filtering recommendation method was presented based on dynamic social behavior and users’ background information.As the result of user annotation behavior,variable social tags can reflect the changes of user social behavior.Firstly,the similarities of users’ dynamic preferences are calculated based on users’ social tags.Secondly,the similarities between users are calculated based on users’ background information.Finally,the similarities of user rating are calculated based on time weight,and the above three similarities are integrated to get the nearest neighbor set for targeted users to provide more accurate individual recommendation.The experimental results show that the new method can not only improve the accuracy of recommendation,but also solve the problems of data sparsity and cold-start.

Key words: Recommendation precision,Cold-start,Social tags,Users’ background information,Dynamic social beha-vior,Time weight

[1] 于洪,李转运.基于遗忘曲线的协同过滤推荐算法[J].南京大学学报:自然科学版,2010,6(5):520-527
[2] 冯勇,李军平,徐红艳,等.基于社会网络分析的协同过滤推荐方法改进[J].计算机应用,2013,3(3):841-844
[3] Eleftherios T,Yannis M.Product recommendation and ratingprediction based on multi-modal social networks[C]∥Pocee-dings of the 5th ACM Conference on Recommender Systems.New York:ACM Press,2011:61-68
[4] 贾大文,曾承,彭智勇,等.一种基于用户偏好自动分类的社会媒体共享和推荐方法[J].计算机学报,2012,5(11):2381-2391
[5] 顾亦然,陈敏.一种三部图网络中标签时间加权的推荐方法[J].计算机科学,2012,9(8):96-98,9
[6] Cheng Yuan,Qiu Guang,Bu Jia-jun,et al.Model bloggers’ interests based on forgetting mechanism[C]∥Proceedings of the 17th International Conference on World Wide Web.New York:ACM Press,2008:1129-1130
[7] 庄景明,王明文,叶茂盛.基于内容过滤的农业信息推荐系统[J].计算机工程,2012,8(11):38-41
[8] Zhou Tao,Jiang L L,Su R Q,et al.Effect of initial configuration on network-based recommendation[J].Europhys Lett,2008,81:58004
[9] 赵琴琴,鲁凯,王斌.SPCF:一种基于内存的传播史协同过滤推荐算法[J].计算机学报,2013,6(3):671-676

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!