《计算机应用研究》|Application Research of Computers

基于非负多矩阵分解的微博网络信息推荐

Information recommendation in microblogging network based on non-negative multiple matrix factorization

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张国英,武浩,蔡光卉,何敏,余江,徐涛
机构 1.云南大学 信息学院,昆明 650091;2.云南红岭云网络科技有限公司,昆明 650000
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)09-2718-05
DOI 10.3969/j.issn.1001-3695.2017.09.034
摘要 微博网站作为一种流行的社交媒体形式,在为用户提供丰富信息和服务的同时,也带来了信息超载问题。如何利用微博网络为用户推荐有价值的信息,以缓解信息超载问题变得日益重要。根据微博网络的有向性以及建立关注关系的随意性等特点,提出了一种基于非负多矩阵分解的微博网络推荐方法,综合考虑了用户之间的关注关系、用户与微博内容的转发关系,以及微博内容与主题的所属关系等多源信息。基于新浪微博数据集进行了微博内容推荐实验,结果表明基于非负多矩阵分解的方法能够有效利用微博网络中的多维信息,显著提高推荐准确度。该方法不仅能挖掘出微博内容的主题,还能挖掘出用户间的关联关系,可推广到对用户进行好友和主题的推荐。
关键词 微博网络;推荐;非负多矩阵分解;好友;主题
基金项目 云南省科技创新强省计划资助项目(2014AB016)
国家自然科学基金资助项目(61562090)
云南省应用基础研究计划面上项目(2013FB009)
本文URL http://www.arocmag.com/article/01-2017-09-034.html
英文标题 Information recommendation in microblogging network based on non-negative multiple matrix factorization
作者英文名 Zhang Guoying, Wu Hao, Cai Guanghui, He Min, Yu Jiang, Xu Tao
机构英文名 1.SchoolofInformationScience&Engineering,YunnanUniversity,Kunming650091,China;2.YunnanHonglingyunNetworkTechnologyCo.Ltd,Kunmimg650000,China
英文摘要 As a popular form of social media, micro-blog Web site provides rich information and services to users, at the same time it also brings the problem of information overload. How to use the microblogging network to recommend valuable information for users, to ease the problem of information overload, becomes increasingly important. According to the orientation, the randomness followed and other characteristics in the microblogging network, this paper proposed a microblogging network recommendation based on non-negative multiple matrix factorization, comprehensively considering the follow relationship among users, the repost relationship between users and micro-blog content, and the ownership relationship between micro-blog content and topic and other multi-source information.Experiment on Sina Weibo dataset for the micro-blog content recommendation, the results show that the method based on non-negative multiple matrix factorization, can effectively use the multidimensional information in microblogging network, significantly improve the accuracy of recommendation. This method can not only dig out the theme of micro-blog content, but also dig out the relationship among users, and can be extended to recommend friends and topics to users.
英文关键词 microblogging network; recommendation; non-negative multiple matrix factorization; friends; topics
参考文献 查看稿件参考文献
  [1] Dong Anlei, Zhang Ruiqiang, Kolari P, et al. Time is of the essence:improving recency ranking using Twitter data[C] //Proc of the 19th Internatonal Conference on World Wide Web. New York:ACM Press, 2010:331-340.
[2] Chen Jilin, Nairn R, Nelson L, et al. Short and Tweet:experiments on recommending centent from information streams[C] // Proc of the 28th International Conference on Human Factors in Computing Systems. New York:ACM Press, 2010:1185-1194.
[3] Abel F, Gao Qi, Houben G, et al. Analyzing user modeling on Twitter for personalized news recommendations[C] // Proc of the 19th International Conference on User Modeling, Adaption and Personalization. Berlin:Springer, 2011:1-12.
[4] Phelan O, Mccarthy K, Smyth B, et al. Using Twitter to recommen-dreal-time topical news[C] //Proc of ACM Conference on Recommender Systems. New York:ACM Press, 2009:385-388.
[5] 王晟, 王子琪, 张铭. 个性化微博推荐算法[J] . 计算机科学与探索, 2012, 6(10):895-902.
[6] Xia Wei, He Yanxiang, Tian Ye, et al. Feature expansion for microblogging text based on latent Dirichlet location with user feature[C] //Proc of the 6th IEEE Joint International Information Technology and Artificial Intelligence Conference. Washington DC:IEEE Computer Society, 2011:228-32.
[7] 陈文涛, 张小明, 李舟军. 构建微博用户兴趣模型的主题模型的分析[J] . 计算机科学, 2013, 40(4):127-135.
[8] 仇钧. 基于微博社会网络的用户兴趣模型研究[D] . 上海:上海交通大学, 2013.
[9] Takeuchi K, Ishiguro K, Kimura A, et al. Non-negative multiple matrix factorization[C] //Proc of the 23th International Joint Conference on Artificial Intelligence. New York:ACM Press, 2013:1713-1720.
[10] Yin Zhijun, Gupta M, Weninger T, et al. LINKREC:a unified framework for link recommendation with user attributes and graph structure[C] //Proc of the 19th International Conference on World Wide Web. New York:ACM Press, 2010:1211-1212.
[11] Dimicco J M, Millen D R, Geyer W, et al. Motivations for social networking at work[C] //Proc of ACM Conference on Computer Supported Cooperative Work. New York:ACM Press, 2008:711-720.
[12] Guy I, Ronen I, Wilcox E. Do you know?Recommending people to invite into your social network[C] //Proc of the 14th International Conference on Intelligent User Interfaces. New York:ACM Press, 2009:77-86.
[13] Granovetter M S. The strength of weak ties[J] . Social Science Electronic Publishing, 2015, 78(2):1360-1380.
[14] 徐戈, 王厚峰. 自然语言处理中主题模型的发展[J] . 计算机学报, 2011, 34(8):1423-1436.
[15] Steyvers M, Wmyth P, Rosen-Zvi M, et al. Probalistic author-topic models for information discovery[C] //Proc of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2004:306-315.
[16] Zhou Ding, Manavoglu E, Li Jia, et al. Probalistic models for disco-vering e-communities[C] //Proc of the 15th International Conference on World Wide Web. New York:ACM Press, 2006:173-182.
[17] McCallum A, Wang Xuerui, Corradaemmanuel A. Topic and role discovery in social networks with experiments on enron and academic email[J] . Journal of Artificial Intelligence Research, 2007, 30(1):249-272.
[18] Cha Y, Bi Bin, Heieh C, et al. Incoporating popularity in topic mo-dels for social network analysis[C] //Proc of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2013:223-232.
[19] Cha Y, Cho J. Social-network analysis using topic models[C] //Proc of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2012:565-574.
[20] Fawcett T. Introduction to ROC analysis[J] . Pattern Recognition Letters, 2006, 27(8):861-874.
[21] Wu Hao, Pei Yijian, Li Bo, et al. Item recommendation in collaborative tagging systems via heuristic data fusion[J] . Knowledge-Based Systems, 2015, 75(C):124-140.
[22] http://www. datatang. com/data/46758/[EB/OL] .
[23] Salakhutdinov R, Mnih A. Probabilistic matrix factorization[C] //Proc of the 21st Annual Conference on Neural Information Processing Systems. 2007:1257-1264.
[24] Koren Y. Factor in the neighbors:scalable and accurate collaborative filtering[J] . ACM Trans on Knowledge Discovery from Data, 2010, 4(1):1-24.
收稿日期 2016/6/21
修回日期 2016/8/8
页码 2718-2722,2726
中图分类号 TP391
文献标志码 A