[1]胡胜利,谭 青.融合用户评论的矩阵分解推荐算法[J].常州大学学报(自然科学版),2018,30(04):69-75.[doi:10.3969/j.issn.2095-0411.2018.04.012]
　HU Shengli,TAN Qing.Matrix Factorization Recommendation Algorithm Combining Users’ Reviews[J].Journal of Changzhou University(Natural Science Edition),2018,30(04):69-75.[doi:10.3969/j.issn.2095-0411.2018.04.012]
点击复制

融合用户评论的矩阵分解推荐算法()
分享到：

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第30卷
期数:
2018年04期
页码:
69-75
栏目:
计算机与信息工程
出版日期:
2018-07-28

文章信息/Info

Title:
Matrix Factorization Recommendation Algorithm Combining Users’ Reviews
作者:
胡胜利; 谭 青
安徽理工大学 计算机科学与工程学院,安徽 淮南 232001
Author(s):
HU Shengli;  TAN Qing
School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China
关键词:
矩阵分解;  用户评论;  主题模型;  正则化项;  推荐算法
Keywords:
matrix factorization;  textual review;  topic model;  regularization term;  recommendation algorithm
分类号:
TK 8
DOI:
10.3969/j.issn.2095-0411.2018.04.012
文献标志码:
A
摘要:
针对传统协同过滤算法中存在的数据稀疏性和单一利用用户的评分行为进行推荐的问题,提出了一种融合用户评论的矩阵分解推荐算法(USRMF)。该算法首先利用主题模型产生用户评论文本的主题分布,并结合评分提取出准确的用户兴趣和物品特征,然后结合用户兴趣和物品特征,通过余弦相似度计算分别得到用户和物品的最近邻,最后将最近邻的正则化项引入到矩阵分解模型中。实验中将USRMF算法与传统的协同过滤算法、正则化矩阵分解算法进行比较,结果表明USRMF算法在稀疏的数据集上能够提高推荐的准确度。
Abstract:
In order to solve the problems of data sparseness and only using the user’s rating behavior to recommend in the traditional collaborative filtering algorithm,a kind of matrix factorization recommendation algorithm combining users’ reviews was proposed. First, the algorithms utilized topic model to generate review topics distribution, and extracted accurate user interests and items characteristics by integrating the score. Then, combined with users’ interests and item characteristics, the nearest neighbors of users and items were calculated according to the cosine similarity. Last, the nearest regularization terms were introduced into the matrix decomposition model.The USRMF was compared with the traditional collaborative filtering algorithm and the regularization matrix decomposition algorithm.The experimental result shows that the USRMF can improve the accuracy of recommendation in sparse datasets.

参考文献/References:


[1]XIANG L. Recommendation system practice[M].Beijing: Posts & Telecom Press,2012:41-43.
[2]PARK Y,PARK S,JUNG W,et al.Reversed CF: a fast collaborative filtering algorithm using a k-nearest neighbor graph[J].Expert Systems with Applications,2015,42(8):4022-4028.
[3]荣辉桂,火生旭,胡春华,等.基于用户相似度的协同过滤推荐算法[J].通信学报,2014,35(2):16-24.
[4]王升升,赵海燕,陈庆奎,等. 基于社交标签和社交信任的概率矩阵分解推荐算法[J]. 小型微型计算机系统,2016(5):921-926.
[5]熊丽荣,刘坚,汤颖.基于联合概率矩阵分解的移动社会化推荐[J]. 计算机科学,2016(9):255-260.
[6]张明,郭娣. 一种优化标签的矩阵分解推荐算法[J]. 计算机工程与应用,2015(23):119-124.
[7]MANZATO M G. Supporting implicit feedback on recommender systems with metadata awareness[C]//SAC 2013: Proceedings of the 28th Annual ACM Symposium on Applied Computing.New York: ACM,2013:908-913.
[8]KRASNOSHCHOK O,LAMO Y.Extended content-boosted matrix factorization algorithm for recommender systems[J].Procedia Computer Science,2014,35: 417-426.
[9]AL-QAHERI H,BANERJEE S.Design and implementation of a policy recommender system towards social innovation:an experience with hybrid machine learning[M]. [S.l.]: Springer International Publishing,2015: 237-250.
[10]JAKOB N,WEBERS H,MLLERM C,et al.Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations[C]//Proc of the 1st International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion.Hong Kong:[s.n.],2009: 57-64.
[11]王建,黄佳进. LDA-RR:一种基于评分和评论的推荐方法[J]. 计算机科学,2017(2):267-269,305.
[12]BILGE A,KALELI C. A multi-criteria item-based collaborative filtering framework[C]//International Joint Conference on Computer Science and Software Engineering(JCSSE). [S.l.]: IEEE,2014:18-22.
[13]刘慧婷,陈艳,肖慧慧. 基于用户偏好的矩阵分解推荐算法[J]. 计算机应用,2015(S2):118-121.
[14]BLEID M,NGA Y,JORDAN M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3(4/5):993-1022.
[15]CELMA M,HERRERA P.A new approach to evaluating novel recommendations[C]//RecSys 2008: Proceedings of the 2008 ACM Conference on Recommender Systems.New York: ACM,2008:179-186.

备注/Memo

备注/Memo:
基金项目:安徽理工大学硕士研究生创新基金项目(2017CX2112)。
作者简介:胡胜利(1978—),男,回族,安徽淮南人,硕士,副教授。E-mail:slhu@aust.edu.cn
更新日期/Last Update: 2018-07-30