适应用户兴趣变化的改进型协同过滤算法

doi:10.11772/j.issn.1001-9081.2016.08.2087

计算机应用 ›› 2016, Vol. 36 ›› Issue (8): 2087-2091.DOI: 10.11772/j.issn.1001-9081.2016.08.2087

• 第六届中国数据挖掘会议(CCDM 2016) • 上一篇下一篇

适应用户兴趣变化的改进型协同过滤算法

胡伟健¹, 滕飞^1,2, 李灵芳¹, 王欢³

1. 西南交通大学信息科学与技术学院, 成都 610031;
2. 计算机软件新技术国家重点实验室(南京大学), 南京 210023;
3. 电子科技大学计算机科学与工程学院, 成都 611731

收稿日期:2016-03-01 修回日期:2016-05-15 出版日期:2016-08-10 发布日期:2016-08-10
通讯作者: 滕飞
作者简介:胡伟健(1990-),男,内蒙古包头人,硕士研究生,CCF会员,主要研究方向:云计算、推荐系统;滕飞(1984-),女,山东泰安人,讲师,博士,主要研究方向:云计算、并行计算;李灵芳(1991-),女,云南红河人,硕士研究生,主要研究方向:数据挖掘、隐私保护;王欢(1991-),男,安徽淮南人,硕士研究生,主要研究方向:计算机网络、云计算。
基金资助:
网络智能信息处理四川省高校重点实验室开放课题资助项目（SZJJ2014-049）。

Improved adaptive collaborative filtering algorithm to change of user interest

HU Weijian¹, TENG Fei^1,2, LI Lingfang¹, WANG Huan³

1. School of Information Science and Technology, Southwest Jiaotong University, Chengdu Sichuan 610031, China;
2. State Key Laboratory for Novel Software Technology(Nanjing University), Nanjing Jiangsu 210023, China;
3. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu Sichuan 611731, China

Received:2016-03-01 Revised:2016-05-15 Online:2016-08-10 Published:2016-08-10
Supported by:
This work is partially supported by the National Nature Science Foundation of China (61379114, 61533020).

摘要/Abstract

摘要： 协同过滤算法可以根据用户的历史行为记录去预测其可能喜欢的物品，是现在业界应用极为广泛的推荐算法。但传统的协同过滤算法并没有考虑到用户兴趣的概念漂移，在一些基于时间的协同过滤算法中对推荐时效性的考虑也有所欠缺。针对这些问题，结合用户兴趣随时间转移的特点，改进了相似度的度量方法，同时引入一种增强的时间衰减模型来度量预测值，并将这两种方式有机地结合起来，解决了用户兴趣的概念漂移问题并考虑了推荐算法的时效性。仿真实验中，分别在不同的数据集中对比了该算法与UserCF、TCNCF、PTCF以及TimeSVD++算法的预测评分准确度和TopN推荐准确度。实验结果表明，改进算法能够降低预测评分的均方根误差（RMSE），并在TopN推荐准确度上均优于对比算法。

关键词: 协同过滤, 个性化推荐, 用户兴趣, 欧氏距离, 时效性

Abstract: As a widely used recommendation algorithm in the industry, collaborative filtering algorithm can predict the likely favorite items based on the user's historical behavior records. However, the traditional collaborative filtering algorithms do not take into account the drifting of user interests, and there are also some deficiencies when the recommendation's timeliness is considered. To solve these problems, the measure method of similarity was improved by combining with the characteristics of user interests change with time. At the same time, an enhanced time attenuation model was introduced to measure the predictive value. By combining these two ways together, the concept drifting problem of user interests was solved and the timeliness of the recommendation algorithm was also considered. In the simulation experiment, predictive scoring accuracy and TopN recommendation accuracy were compared among the proposed algorithm, UserCF, TCNCF, PTCF and TimesSVD++ algorithm in different data sets. The experimental results show that the improved algorithm can reduce the Root Mean Square Error (RMSE) of the prediction score, and it is better than all the compared algorithms on the accuracy of TopN recommendation.

Key words: collaborative filtering, personalized recommendation, user interest, Euclidean distance, chronergy

中图分类号:

胡伟健, 滕飞, 李灵芳, 王欢. 适应用户兴趣变化的改进型协同过滤算法[J]. 计算机应用, 2016, 36(8): 2087-2091.

HU Weijian, TENG Fei, LI Lingfang, WANG Huan. Improved adaptive collaborative filtering algorithm to change of user interest[J]. Journal of Computer Applications, 2016, 36(8): 2087-2091.

参考文献

[1] RESNICK P,IACOVOU N,SUCHAK M,et al.GroupLens:an open architecture for collaborative filtering of netnews[C]//CSCW'94:Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work.New York:ACM,1994:175-186.
[2] ADOMAVICIUS G,TUZHILIN A.Toward the next generation of recommender systems:a survey of the state-of-the-art and possible extensions[J].IEEE Transactions on Knowledge&Data Engineering,2005,17(6):734-749.
[3] SCHAFER J B,KONSTAN J,RIEDL J.Recommender systems in E-commerce[C]//EC'99:Proceedings of the 1st ACM Conference on Electronic Commerce.New York:ACM,1999:158-166.
[4] JAYAWARDANA C,HEWAGAMAGE K P,HIRAKAWA M.A personalized information environment for digital libraries[J].Information Technology&Libraries,2001,20(4):185-196.
[5] KONSTAN J A,MILLER B N,MALTZ D,et al.GroupLens:applying collaborative filtering to Usenet news[J].Communications of the ACM,2000,40(3):77-87.
[6] 郑先荣,曹先彬.线性逐步遗忘协同过滤算法的研究[J].计算机工程,2007,33(6):72-73.(ZHENG X R,CAO X B.Research on lineal gradual forgetting collaborative filtering algorithm[J].Computer Engineering,2007,33(6):72-74.)
[7] 任磊.一种结合评分时间特性的协同推荐算法[J].计算机应用与软件,2015,32(5):112-115.(REN L.A collaborative recommendation algorithm in combination with rating time characteristic[J].Computer Applications and Software,2015,32(5):112-115.)
[8] 丛晓琪,杨怀珍,刘枚莲.基于时间加权的协同过滤算法研究[J].计算机应用与软件,2009,26(8):120-121.(CONG X Q,YANG H Z,LIU M L.On collaborative filtering algorithm based on time weight[J].Computer Applications and Software,2009,26(8):120-121.)
[9] OWEN S,ANIL R,DUNNING T,et al.Mahout in Action[M].Greenwich,CT:Manning Publications,2011:34-47.
[10] 许海玲,吴潇,李晓东,等.互联网推荐系统比较研究[J].软件学报,2009,20(2):350-362.(XU H L,WU X,LI X D,et al.Comparison study of Internet recommendation system[J].Journal of Software,2009,20(2):350-362.)
[11] 李佳,陈亚军.基于时间和共同评分项目数的协同过滤算法研究[J].软件导刊,2015,14(7):61-63.(LI J,CHEN Y J.A filtering algorithm research based on time and the number of common grading[J].Software Guide,2015,14(7):61-63.)
[12] 孙光辉.基于时间效应和用户兴趣变化的改进推荐算法研究[D].北京:北京邮电大学,2014:10-19.(SUN G H.Research of improved recommendation algorithm based on time effect and changes in users interest[D].Beijing:Beijing University of Posts and Telecommunications,2014:10-19.)
[13] KOREN Y.Collaborative filtering with temporal dynamics[J].Communications of the ACM,2010,53(4):89-97.
[14] XIONG L,CHEN X,HUANG T K,et al.Temporal collaborative filtering with bayesian probabilistic tensor factorization[C]//SDM 2000:Proceedings of the 2010 SIAM International Conference on Data Mining.Philadelphia,PA:SIAM,2010:211-222.
[15] FAN X,HU Y,ZHANG R,et al.Modeling temporal effectiveness for context-aware Web services recommendation[C]//ICWS 2015:Proceedings of the 2015 IEEE International Conference on Web Services.Washington,DC:IEEE Computer Society,2015:225-232.
[16] 范家兵,王鹏,周渭博,等.在推荐系统中利用时间因素的方法[J].计算机应用,2015,35(5):1324-1327.(FAN J B,WANG P,ZHOU W B,et al.Method by using time factors in recommender system[J].Journal of Computer Applications,2015,35(5):1324-1327.)
[17] 项亮.推荐系统实践[M].北京:人民邮电出版社,2012:35-77.(XIANG L.Recommended System Practice[M].Beijing:Posts and Telecom Press,2012:35-77.)
[18] 王岚,翟正军.基于时间加权的协同过滤算法[J].计算机应用,2007,27(9):2302-2303.(WANG L,ZHAI Z J.Collaborative filtering algorithm based on time weight[J].Journal of Computer Applications,2007,27(9):2302-2303.)

适应用户兴趣变化的改进型协同过滤算法

Improved adaptive collaborative filtering algorithm to change of user interest

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	包玄, 陈红梅, 肖清. 融入时间的兴趣点协同推荐算法[J]. 计算机应用, 2021, 41(8): 2406-2411.
[2]	刘欢, 李晓戈, 胡立坤, 胡飞雄, 王鹏华. 基于知识图谱驱动的图神经网络推荐模型[J]. 计算机应用, 2021, 41(7): 1865-1870.
[3]	孙鹤立, 徐统, 何亮, 贾晓琳. 融合用户历史行为与社交关系的个性化社交事件推荐方法[J]. 计算机应用, 2021, 41(2): 324-329.
[4]	李翔锟, 贾彩燕. 融合重叠社区正则化及隐式反馈的协同过滤方法[J]. 计算机应用, 2021, 41(1): 53-59.
[5]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907.
[6]	葛宇, 梁静. 基于相遇概率时效性和重复扩散感知的机会网络消息转发算法[J]. 计算机应用, 2020, 40(5): 1397-1402.
[7]	陈曦, 梅广, 张金金, 许维胜. 融合知识图谱和协同过滤的学生成绩预测方法[J]. 计算机应用, 2020, 40(2): 595-601.
[8]	邓凯, 黄佳进, 秦进. 基于物品的统一推荐模型[J]. 计算机应用, 2020, 40(2): 530-534.
[9]	张文龙, 钱付兰, 陈洁, 赵姝, 张燕平. 基于双重最相关注意力网络的协同过滤推荐算法[J]. 计算机应用, 2020, 40(12): 3445-3450.
[10]	樊玮, 谢聪, 肖春景, 曹淑燕. 基于组合类别空间的随机游走推荐算法[J]. 计算机应用, 2019, 39(4): 984-988.
[11]	雷曼, 龚琴, 王纪超, 王保群. 基于标签权重的协同过滤推荐算法[J]. 计算机应用, 2019, 39(3): 634-638.
[12]	许朝, 孟凡荣, 袁冠, 李月娥, 刘肖. 融合地点影响力的兴趣点推荐算法[J]. 计算机应用, 2019, 39(11): 3178-3183.
[13]	刘彤, 曾诚, 何鹏. 基于用户网络嵌入的民宿房源推荐方法[J]. 计算机应用, 2019, 39(11): 3398-3402.
[14]	徐玲玲, 曲志坚, 徐红博, 曹小威, 刘晓红. 融合信任信息的欧氏嵌入推荐算法[J]. 计算机应用, 2019, 39(10): 2829-2833.
[15]	杨帅, 王鹃. 基于堆栈降噪自编码器改进的混合推荐算法[J]. 计算机应用, 2018, 38(7): 1866-1871.