计算机科学 ›› 2016, Vol. 43 ›› Issue (12): 168-172.doi: 10.11896/j.issn.1002-137X.2016.12.030

• 数据挖掘 • 上一篇    下一篇

基于改进鱼群算法与张量分解的社会化标签推荐模型

张浩,何杰,李慧宗   

  1. 淮阴工学院交通工程学院 淮安223003;东南大学交通学院 南京210096,东南大学交通学院 南京210096,合肥工业大学计算机与信息学院 合肥230009
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受江苏省高校哲学社会科学项目(2014SJB688),国家统计局项目(2014LY058),教育部人文社会科学项目(13YJCZH077)资助

Social Tagging Recommendation Model Based on Improved Artificial Fish Swarm Algorithm and Tensor Decomposition

ZHANG Hao, HE Jie and LI Hui-zong   

  • Online:2018-12-01 Published:2018-12-01

摘要: 基于大众分类法(folksonomy)的标签应用已逐渐成为一种重要的互联网内容组织方式,但随着数据规模的海量增长,产生了严重的信息过载问题,而传统的基于“用户-项目”二元关系的个性化推荐算法难以有效应对由“用户-项目-标签”所构成的三元关系。通过对基本人工鱼群算法进行改进,提出一种对标签推荐系统初始数据集进行聚类分析的方法,用以降低标签推荐系统的数据分析规模。在此基础上,综合考虑标签推荐系统中的元素权重以及反映用户偏好的评分信息,将元素权重和评分等级进行加权处理,以处理结果作为张量中的元素,建立了一种新的加权张量模型,并利用动态增量更新的张量分解算法进行模型求解,进而完成个性化的推荐。最后在两个真实的实验数据集上对比分析了所提算法(FTA)与另外两个经典标签推荐算法的推荐性能,实验结果表明FTA算法在准确率和召回率上均具有较好的表现。

关键词: 鱼群算法,聚类分析,张量分解,标签推荐

Abstract: Popular classification (Folksonomy) tag application has gradually become an important way of internet content organization,but with the massive increase in the scale of data,the problem of information overload has been produced.On the other hand,the traditional personalized recommendation algorithm based on the relationship between ‘user-item’ is difficult to have effect on the three elements of the “user-item-label”.Based on the improvement of basic artificial fish swarm algorithm,a clustering analysis method was proposed for the initial data set of the tag recommendation system(TRS),which is used to reduce the scale of the data analysis of the TRS.Based on this,through comprehensive consideration of the label recommendation system element weights and the reflection of user preference score information,and by weighted processing of the element weights and grades as the elements in the tensor,a new weighted tensor model was established,and the model was solved by the dynamic incremental updating of the tensor decomposition algorithm,completing the personalized recommendation.Finally,on two real experimental data sets,the proposed algorithm (FTA) and the other two classic tag recommendation algorithms were compared and analyzed.The experimental results show that the FTA algorithm has better performance in the recall rate and precision rate.

Key words: Artificial fish swarm algorithm,Clustering analysis,Tensor decomposition,Tag recommendation

[1] Lü Lin-yuan,Medo M,Yeung C H,et al.Recommender systems [DB/OL].[2012-02-06].http://arxiv.org/abs/1202.1112
[2] Chen Chao,Zhang Ying-chao,Miao Jin.A collaborative filtering recommender algorithm based on tripartite network[J].Journal of Nanjing University of Information Science and Technology(Natural Science Edition),2010,2(4):337-339(in Chinese) 陈超,张颖超,缪进.一种基于三部图网络的协同过滤算法[J].南京信息工程大学学报(自然科学版),2010,2(4):337-339
[3] Liao Zhi-Fang,Li Ling,Liu Li-Min,et al.A Tripartite Decomposition of Tensor for Social Tagging[J].Chinese Journal of Computers,2012,35(12):2625-2632(in Chinese) 廖志芳,李玲,刘丽敏,等.三部图张量分解标签推荐算法[J].计算机学报,2012,35(12):2625-2632
[4] Symeonidis P,Nanopoulos A,Manolopoulos Y.A unified framework for providing recommendations in social tagging systems based on ternary semantic analysis[J].IEEE Transactions on Knowledge and Data Engineer,2010,22(2):179-192
[5] Sun Ling-fang,Li Shuo-peng.Social tagging recommendation sy-stem based on K-means cluster and tensor decomposition [J].Journal of Jiangsu University of Science and Technology( Natural Science Edition),2012,26(6):597-601(in Chinese) 孙玲芳,李烁朋.基于K-means聚类与张量分解的社会化标签推荐系统研究[J].江苏科技大学学报(自然科学版),2012,6(6):597-601
[6] Wang Long,Wang Jia-lun,Cheng Zhuan-li,et al.PersonalizedMedicine Recommendation Based on Tensor Decomposition[J].Computer Science,2015,42(5):225-229(in Chinese) 王龙,王嘉伦,程转丽,等.基于张量分解的药品个性化推荐[J].计算机科学,2015,2(5):225-229
[7] Fouzia J,Shah K,Amna M,et al.Semantics discovery in social tagging systems:A review[J].Multimedia Tools and Applications,2016,5(1):573-605
[8] 江铭炎,袁东风.人工鱼群算法及其应用[M].科学出版社,2012
[9] Peng Yong,Tang Guo-lei,Xue Zhi-shun.Optimal operation of cascade reservoirs based on improved artificial fish swarm algorithm[J].Systems Engineering-Theory & Practice,2011,6(6):1118-1125(in Chinese) 彭勇,唐国磊,薛志春.基于改进人工鱼群算法的梯级水库群优化调度[J].系统工程理论与实践,2011,6(6):1118-1125
[10] Liao Yu-lei,Liu Peng,Wang Jian,et al.Control parameter optimization for the unmanned surface vehicle with the improved artificial fish swarm algorithm[J].Journal of Harbin Engineering University,2014,5(7):800-806(in Chinese) 廖煜雷,刘鹏,王建,等.基于改进人工鱼群算法的无人艇控制参数优化[J].哈尔滨工程大学学报,2014,5(7):800-806
[11] Chen Guang-zhou,Wang Jia-quan,Li Chuan-jun,et al.An im-proved artificial fish swarm algorithm and its applications [J].Systems Engineering,2009,7(12):105-110(in Chinese) 陈广洲,汪家权,李传军,等.一种改进的人工鱼群算法及其应用[J].系统工程,2009,7(12):105-110
[12] Weng S S,Lin B S,Chen W T.Using contextual information and multidimensional approach for recommendation [J].Expert Systems with Applications,2007,36(2):1268-1279
[13] Li Gui,Wang Shuang,Li Zheng-yu,et al.Personalized Tag Re-commendation Algorithm Based on Tensor Decomposition[J].Computer Science,2015,2(2):267-273(in Chinese) 李贵,王爽,李征宇,等.基于张量分解的个性化标签推荐算法[J].计算机科学,2015,42(2):267-273
[14] Zou B Y,Li C P,Tan L W,et al.Social recommendations based on user trust and tensor factorization[J].Journal of Software,2014,5(12):2852-2864(in Chinese) 邹本友,李翠平,谭力文.等.基于用户信任和张量分解的社会网络推荐[J].软件学报,2014,25(12):2852-2864
[15] Milicevic A K,Nanopoulos A,MirjanaIvanovic.Social tagging in recommender systems:a survey of the state-of-the-art and possible extensions[J].Artificial Intelligence Review,2010,33(1):187-209

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!