Please wait a minute...
Advanced Search
数据分析与知识发现  2017, Vol. 1 Issue (3): 38-45     https://doi.org/10.11925/infotech.2096-3467.2017.03.05
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于改进张量分解模型的个性化推荐算法研究*
陈梅梅(), 薛康杰
东华大学旭日工商管理学院 上海 200051
Personalized Recommendation Algorithm Based on Modified Tensor Decomposition Model
Chen Meimei(), Xue Kangjie
Glorious Sun School of Business & Management, Donghua University, Shanghai 200051, China
全文: PDF (742 KB)   HTML ( 28
输出: BibTeX | EndNote (RIS)      
摘要 

目的】在基于张量分解的个性化推荐中, 解决因UGC标签冗余、热门标签和资源影响用户个性化兴趣所导致的推荐准确性降低问题。【方法】提出一种改进的基于张量分解模型的个性化推荐算法, 引入标签综合共现结合谱聚类的方法, 借鉴TF-IDF中IDF的思想提出一种基于共现标签和资源的热门惩罚机制, 对基于<用户, 标签簇, 资源>三元关系的初始张量进行重新定义。【结果】基于Last.fm数据集的仿真实验结果表明, 从准确率、召回率和F1值各项指标上, 本文提出的算法均有良好表现, 综合共现谱聚类的引入使得推荐算法在F1值上平均提升5.91%, 基于IDF改进初始张量后的推荐算法在F1值上平均提升1.29%。【局限】未针对其他领域的数据集进行验证, 如微博、Delicious等。【结论】基于改进的张量分解模型的个性化推荐算法能够显著提高准确性, 有利于社交网络环境下提供更令用户满意的资源。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
陈梅梅
薛康杰
关键词 个性化推荐UGC标签标签共现谱聚类张量分解    
Abstract

[Objective] This paper tries to improve the prediction accuracy of personalized recommendation algorithm based on the tensor decomposition model. [Methods] First, we proposed a new tensor model using spectral clustering technique based on combined tag co-occurrence. Second, we established a penalty scheme on popular tag and resource co-occurrence with the help of IDF in TF-IDF. Finally,we re-defined the initial tensor on the triplets of user, tag cluster, and resource. [Results] We examined the proposed model with dataset from Last.fm and found its precision, recall and F1 measure outperformed other algorithms. The F1 measures were increased by 5.91% and 1.29% thanks to the two proposed modifictions based on clustering and IDF. [Limitations] The proposed algorithm should be further evaluated with datasets from Weibo, Delicious, and other resources. [Conclusions] The new algorithm based on advanced tensor decomposition model could significantly improve the accuracy of resources recommendation to satisfy social network system users’ information needs.

Key wordsPersonalized Recommendation    UGC    Tag    Tag Co-occurrence    Spectral Clustering    Tensor Decomposition
收稿日期: 2016-11-10      出版日期: 1985-09-25
:  F224.39 TP391 TP181  
基金资助:*本文系国家社会科学基金项目“中国特色的网络消费调查研究”(项目编号: 10BGL027)的研究成果之一
引用本文:   
陈梅梅, 薛康杰. 基于改进张量分解模型的个性化推荐算法研究*[J]. 数据分析与知识发现, 2017, 1(3): 38-45.
Chen Meimei,Xue Kangjie. Personalized Recommendation Algorithm Based on Modified Tensor Decomposition Model. Data Analysis and Knowledge Discovery, 2017, 1(3): 38-45.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.03.05      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2017/V1/I3/38
  4种算法在准确率-召回率曲线上的对比
  4种算法在F1指标上的对比
数据集 准确性指标 CoSCluIDF CoSClu KmeansIDF TD
Tag8 Precision 22.69% 22.56% 22.38% 11.39%
Recall 43.61% 43.36% 42.94% 21.32%
F1 28.21% 28.05% 27.80% 13.99%
Tag20 Precision 23.67% 23.05% 22.54% 12.20%
Recall 45.80% 44.59% 43.59% 23.05%
F1 29.48% 28.71% 28.07% 15.03%
  推荐平均准确性指标对比
[1] Moens M F, Li J, Chua T S.Mining User Generated Content[M]. CRC Press, 2014: 7-9.
[2] Marinho L B, Nanopoulos A, Schmidt-Thieme L, et al.Social Tagging Recommender Systems[M]. USA: Springer US, 2011: 615-644.
[3] Hitchcock F L.The Expression of a Tensor or a Polyadic as a Sum of Products[J]. Journal of Mathematics & Physics, 1927, 6(1): 164-189.
doi: 10.1002/sapm192761164
[4] Symeonidis P, Nanopoulos A, Manolopoulos Y.Tag Recommendations Based on Tensor Dimensionality Reduction[C]//Proceedings of the 2008 ACM Conference on Recommender Systems, Lausanne, Switzerland. ACM, 2008: 43-50.
[5] 廖志芳, 王超群, 李小庆, 等. 张量分解的标签推荐及新用户标签推荐算法[J]. 小型微型计算机系统, 2013, 34(11): 2472-2476.
doi: 10.3969/j.issn.1000-1220.2013.11.011
[5] (Liao Zhifang, Wang Chaoqun, Li Xiaoqing, et al.Tag Recommendation and New User Tag Recommendation Algorithms Based on Tensor Decomposition[J]. Journal of Chinese Computer Systems, 2013, 34(11): 2472-2476.)
doi: 10.3969/j.issn.1000-1220.2013.11.011
[6] Rendle S, BalbyMarinho L, Nanopoulos A, et al. Learning Optimal Ranking with Tensor Factorization for Tag Recommendation[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2009: 727-736.
[7] 武慧娟, 徐宝祥, 王艳艳. 基于张量分解的个性化信息推荐方法优化研究[J]. 情报科学, 2014, 32(6): 134-137.
[7] (Wu Huijuan, Xu Baoxiang, Wang Yanyan.Optimization Research of Personalized Tag Recommendation Method Based on Tensor Decomposition[J]. Information Science, 2014, 32(6): 134-137.)
[8] Celma S, Cano P.From Hits to Niches? or How Popular Artists Can Bias Music Recommendation and Discovery[C]// Proceedings of the 2nd KDD Workshop on Large-Scale Recommender Systems and the Netflix Prize Competition, Las Vegas, Nevada. ACM, 2008: 1-8.
[9] Salton G, Buckley C.Term-weighting Approaches in Automatic Text Retrieval[J]. Information Processing & Management an International Journal, 1988, 24(5): 513-523.
doi: 10.1016/0306-4573(88)90021-0
[10] Fleder D, Hosanagar K.Blockbuster Culture’s Next Rise or Fall: The Impact of Recommender Systems on Sales Diversity[J]. Management Science, 2007, 55(5): 697-712.
[11] 王成, 朱志刚, 张玉侠, 等. 基于用户的协同过滤算法的推荐效率和个性化改进[J]. 小型微型计算机系统, 2016, 37(3): 428-432.
[11] (Wang Cheng, Zhu Zhigang, Zhang Yuxia, et al.Improvement in Recommendation Efficiency and Personalized of User-based Collaborative Filtering Algorithm[J]. Journal of Chinese Computer Systems, 2016, 37(3): 428-432.)
[12] Cantador I, Bellogín A, Vallet D.Content-based Recommendation in Social Tagging Systems[C]// Proceedings of the 4th ACM Conference on Recommender Systems, Barcelona, Spain. ACM, 2010: 237-240.
[13] 项亮. 推荐系统实践[M]. 人民邮电出版社, 2012: 107-108.
[13] (Xiang Liang.Practice of Recommendation System[M]. Posts & Telecom Press, 2012: 107-108.)
[14] Rafailidis D, Daras P.The TFC Model: Tensor Factorization and Tag Clustering for Item Recommendation in Social Tagging Systems[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2013, 43(3): 673-688.
doi: 10.1109/TSMCA.2012.2208186
[15] Gemmell J, Ramezani M, Schimoler T, et al.The Impact of Ambiguity and Redundancy on Tag Recommendation in Folksonomies[C]//Proceedings of the 3rd ACM Conference on Recommender Systems, New York. ACM, 2009: 45-52.
[16] Leginus M, Dolog P, Žemaitis V.Improving Tensor Based Recommenders with Clustering[C]//Proceedings of the 20th International Conference on User Modeling, Adaptation, and Personalization, Montreal, Canada. Springer-Verlag, 2012: 151-163.
[17] Symeonidis P.ClustHOSVD: Item Recommendation by Combining Semantically Enhanced Tag Clustering with Tensor HOSVD[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 46(9): 1-12.
doi: 10.1109/TSMC.2015.2482458
[18] Shepitsen A, Gemmell J, Mobasher B, et al.Personalized Recommendation in Social Tagging Systems Using Hierarchical Clustering[C]//Proceedings of the 2008 ACM Conference on Recommender Systems, Lausanne, Switzerland. ACM, 2008: 259-266.
[19] Li H, Hu X, Lin Y, et al.A Social Tag Clustering Method Based on Common Co-occurrence Group Similarity[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(2): 122-134.
doi: 10.1631/FITEE.1500187
[20] 李瑞敏, 林鸿飞, 闫俊. 基于用户-标签-项目语义挖掘的个性化音乐推荐[J]. 计算机研究与发展, 2014, 51(10): 2270-2276.
doi: 10.7544/issn1000-1239.2014.20130342
[20] (Li Ruimin, Lin Hongfei, Yan Jun.Mining Latent Semantic on User-Tag-Item for Personalized Music Recommendation[J]. Journal of Computer Research and Development, 2014, 51(10): 2270-2276.)
doi: 10.7544/issn1000-1239.2014.20130342
[21] 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 & Data Engineering, 2010, 22(2): 179-192.
doi: 10.1109/TKDE.2009.85
[22] Lathauwer L D, Moor B D, Vandewalle J.On the Best Rank-1 and Rank-(R1, R2,…, RN) Approximation of Higher-Order Tensors[J]. Siam Journal on Matrix Analysis & Applications, 2000, 21(4): 1324-1342.
[23] Kolda T G, Bader B W.Tensor Decompositions and Applications[J]. College & Research Libraries, 2005, 66(4): 294-310.
[24] Pazzani M, Billsus D.Learning and Revising User Profiles: The Identification of Interesting Web Sites[J]. Machine Learning, 1997, 27(3): 313-331.
doi: 10.1023/A:1007369909943
[25] White S, Smyth P.A Spectral Clustering Approach to Finding Communities in Graph[C]//Proceedings of the 2005 SIAM International Conference on Data Mining, Newport Beach, CA, USA. SIAM, 2005: 274-285.
[1] 陆泉, 何超, 陈静, 田敏, 刘婷. 基于两阶段迁移学习的多标签分类模型研究*[J]. 数据分析与知识发现, 2021, 5(7): 91-100.
[2] 吴彦文, 蔡秋亭, 刘智, 邓云泽. 融合多源数据和场景相似度计算的数字资源推荐研究*[J]. 数据分析与知识发现, 2021, 5(11): 114-123.
[3] 丁浩, 艾文华, 胡广伟, 李树青, 索炜. 融合用户兴趣波动时序的个性化推荐模型*[J]. 数据分析与知识发现, 2021, 5(11): 45-58.
[4] 席运江, 杜蝶蝶, 廖晓, 仉学红. 基于超网络的企业微博用户聚类研究及特征分析*[J]. 数据分析与知识发现, 2020, 4(8): 107-118.
[5] 盛嘉祺, 许鑫. 融合主题相似度与合著网络的学者标签扩展方法研究*[J]. 数据分析与知识发现, 2020, 4(8): 75-85.
[6] 叶佳鑫,熊回香,童兆莉,孟秋晴. 在线医疗社区中面向医生的协同标注研究*[J]. 数据分析与知识发现, 2020, 4(6): 118-128.
[7] 魏伟,郭崇慧,邢小宇. 基于语义关联规则的试题知识点标注及试题推荐*[J]. 数据分析与知识发现, 2020, 4(2/3): 182-191.
[8] 马娜,张智雄,吴朋民. 基于特征融合的术语型引用对象自动识别方法研究*[J]. 数据分析与知识发现, 2020, 4(1): 89-98.
[9] 李博诚,张云秋,杨铠西. 面向微博商品评论的情感标签抽取研究 *[J]. 数据分析与知识发现, 2019, 3(9): 115-123.
[10] 夏立新,曾杰妍,毕崇武,叶光辉. 基于LDA主题模型的用户兴趣层级演化研究 *[J]. 数据分析与知识发现, 2019, 3(7): 1-13.
[11] 张怡文,张臣坤,杨安桔,计成睿,岳丽华. 基于条件型游走的四部图推荐方法*[J]. 数据分析与知识发现, 2019, 3(4): 117-125.
[12] 叶佳鑫,熊回香. 基于标签的跨领域资源个性化推荐研究*[J]. 数据分析与知识发现, 2019, 3(2): 21-32.
[13] 聂卉. 结合词向量和词图算法的用户兴趣建模研究 *[J]. 数据分析与知识发现, 2019, 3(12): 30-40.
[14] 毕崇武,叶光辉,李明倩,曾杰妍. 基于标签语义挖掘的城市画像感知研究 *[J]. 数据分析与知识发现, 2019, 3(12): 41-51.
[15] 丁浩,李树青. 基于用户多类型兴趣波动趋势预测分析的个性化推荐方法 *[J]. 数据分析与知识发现, 2019, 3(11): 43-51.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn