基于社会化标注的用户兴趣挖掘

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

清华大学辅仁网/2017-07-07

基于社会化标注的用户兴趣挖掘

扈维,张尧学(

),周悦芝

User preference mining based on social tagging

Wei HU,Yaoxue ZHANG(

),Yuezhi ZHOU

National Laboratory of Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

摘要:

HTML
输出: BibTeX | EndNote (RIS)

摘要用户兴趣挖掘是实现个性化推荐与智能化服务的关键问题。Web2.0引入的社会化标注可以反映用户的潜在兴趣。该文提出一种基于用户标注行为的兴趣建模方法,根据用户与标签的交互模式反映用户的兴趣倾向。从用户对不同标签的“认同度”和“依赖度”两方面衡量用户的标签兴趣,并使用“标签基因”对用户的兴趣进行细粒度分解。来自真实用户数据的实验结果表明,该方法可以有效提高用户兴趣的预测准确度和覆盖率,创建的兴趣模型更加符合用户的真实情况。

关键词 ：用户模型,社会标注,兴趣挖掘

Abstract：User preference mining is one of the key problems in personalized recommendations and intelligent services. Social tagging in web2.0 reflects the user's potential interests. This paper presents a user preference modeling method based on social tagging that predicts user preferences based on interactions between user and tag. The user's “degree of recognition” and “dependency” on an individual tag are combined to evaluate the user's tag preference. The user's interest is then decomposed into a fine-grained result using a “Tag Genome”. Tests based on real data demonstrate that this method significantly improves prediction accuracies and coverage to more accurately match the user's real interests.

Key words：user model social tags data mining

收稿日期: 2013-10-08 出版日期: 2015-04-17

基金资助:国家 “八六三” 高技术项目 (2011AA01A203);国家科技支撑计划项目 (2012BAH13F04)

引用本文:

扈维,张尧学,周悦芝. 基于社会化标注的用户兴趣挖掘[J]. 清华大学学报（自然科学版）, 2014, 54(4): 502-507.
Wei HU,Yaoxue ZHANG,Yuezhi ZHOU. User preference mining based on social tagging. Journal of Tsinghua University(Science and Technology), 2014, 54(4): 502-507.

链接本文:

http://jst.tsinghuajournals.com/CN/或 http://jst.tsinghuajournals.com/CN/Y2014/V54/I4/502

图表:

用户的标签评分示意图

用户的标签评分矩阵图

Sigmoid函数曲线

用户兴趣建模流程图

用户的标签兴趣模型

预测准确率对比

覆盖率对比

标签基因的影响

热门惩罚的影响

参考文献:

[1]	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 and Data Engineering, 2005, 17(6): 734-749.
[2]	Godoy D, Amandi A. User profiling in personal information agents: a survey[J]. The Knowledge Engineering Review, 2005, 20(04): 329-361.
[3]	Resnick P, Iacovou N, Suchak M, et al.GroupLens: an open architecture for collaborative filtering of netnews [C]// Proceedings of the 1994 ACM conference on Computer supported cooperative work. North Carolina: ACM, 1994: 175-186.
[4]	Herlocker J L, Konstan J A, Terveen L G, et al.Evaluating collaborative filtering recommender systems[J]. ACM Transactions on Information Systems (TOIS), 2004, 22(1): 5-53.
[5]	Vig J, Soukup M, Sen S, et al.Tag expression: tagging with feeling [C]// Proceedings of the 23nd annual ACM symposium on User interface software and technology. New York, NY: ACM, 2010: 323-332.
[6]	Li X, Guo L, Zhao Y E. Tag-based social interest discovery [C]// Proceedings of the 17th international conference on World Wide Web.Beijing: ACM, 2008: 675-684.
[7]	王卫平, 王金辉. 基于Tag和协同过滤的混合推荐方法[J]. 计算机工程, 2011, 37(14): 34-35. WANG Weiping, WANG Jinhui. Hybrid recommendation method based on tag and collaborative filtering[J]. Computer Engineering. 2011, 37(14): 34-35. (in Chinese)
[8]	夏宁霞, 苏一丹, 覃华, 等. 社会化标签系统中个性化的用户建模方法[J]. 计算机应用, 2011, 31(6): 1667-1670. XIA Ningxia, SU Yidan, QIN Hua, et al.Method for personalized user profiling in social tagging systems[J]. Journal of Computer Applications, 2011, 31(6): 1667-1670. (in Chinese)
[9]	韩敏, 唐常杰, 段磊, 等. 基于 TF# IDF 相似度的标签聚类方法 &[J]. 计算机科学与探索, 2010, 4(3): 240-245. HAN Min, TANG Changjie, DUAN Lei, et al.TF-IDF similarity based method for tag clustering[J]. Journal of Frontiers of Computer Science & Technology, 2010, 4(3): 240-245. (in Chinese)
[10]	Ramos J. Using tf-idf to determine word relevance in document queries [C]// Proceedings of the FirstInstructional Conference on Machine Learning. Piscataway, NJ: CS536, 2003: 235-239.
[11]	Cosley D, Lam S K, Albert I, et al.Is seeing believing?: how recommender system interfaces affect users' opinions [C]// Proceedings of the SIGCHI conference on Human factors in computing systems. Ft. Lauderdale, FL: ACM, 2003: 585-592.
[12]	Vig J, Sen S, Riedl J. Computing theTag Genome, MC2010319 [R]. Minneapolis, MN: University of Minnesota, 2010.
[13]	Vig J, Sen S, Riedl J. Thetag genome: Encoding community knowledge to support novel interaction[J]. ACM Transactions on Interactive Intelligent Systems (TiiS), 2012, 2(3): 13.

No related articles found!