Infer User Interests via Link Structure Regularization

Infer User Interests via Link Structure Regularization
复制标题

通过链接结构正则化推断用户兴趣

DOI:
10.1145/2499380
复制
发表时间:
2014-04
影响因子:
5
通讯作者:
李晓明
李晓明
中科院分区:
计算机科学3区
文献类型:
--
作者:
王锦鹏;赵鑫;He Yulan;李晓明

文献摘要

参考文献

被引文献

相似文献

从在线社交网络中学习用户兴趣有助于更好地理解用户行为,并为设计以用户为中心的应用程序提供有用的指导。除了分析用户的在线内容,考虑用户在社交网络中的社交联系也很重要。图正则化方法可以充分利用从数据中提取的图结构信息,已广泛应用于各种文本挖掘任务中。以前,图正则化方法在集群假设下操作,即附近的节点更相似,并且相同结构(通常称为集群或流形)上的节点可能相似。我们认为,从复杂的,稀疏的,和动态的社交网络学习用户的兴趣应该是基于链接结构的假设下,节点的相似性进行评估的基础上的本地链接结构,而不是显式的两个节点之间的链接。我们提出了一个正则化框架的基础上的关系二分图,它可以从任何类型的关系。使用Twitter作为我们的案例研究,我们评估我们提出的框架,从社交网络建立从转推关系。定量和定性的实验表明,我们提出的方法优于一些有竞争力的基线学习用户的兴趣在一组预定义的主题。它还提供了上级的结果相比,在转发预测和主题权威识别的基线。
Learning user interests from online social networks helps to better understand user behaviors and provides useful guidance to design user-centric applications. Apart from analyzing users' online content, it is also important to consider users' social connections in the social Web. Graph regularization methods have been widely used in various text mining tasks, which can leverage the graph structure information extracted from data. Previously, graph regularization methods operate under the cluster assumption that nearby nodes are more similar and nodes on the same structure (typically referred to as a cluster or a manifold) are likely to be similar. We argue that learning user interests from complex, sparse, and dynamic social networks should be based on the link structure assumption under which node similarities are evaluated based on the local link structures instead of explicit links between two nodes. We propose a regularization framework based on the relation bipartite graph, which can be constructed from any type of relations. Using Twitter as our case study, we evaluate our proposed framework from social networks built from retweet relations. Both quantitative and qualitative experiments show that our proposed method outperforms a few competitive baselines in learning user interests over a set of predefined topics. It also gives superior results compared to the baselines on retweet prediction and topical authority identification.
DOI: 10.1145/1963405.1963504
发表时间: 2011-03
期刊: --
影响因子: --
作者:
Shaomei Wu;Jake M. Hofman;Winter A. Mason;D. Watts
通讯作者: Shaomei Wu;Jake M. Hofman;Winter A. Mason;D. Watts
DOI: 10.1145/1935826.1935882
发表时间: 2011-02
期刊: --
影响因子: --
作者:
Michael J. Welch;Uri Schonfeld;Dan He;Junghoo Cho
通讯作者: Michael J. Welch;Uri Schonfeld;Dan He;Junghoo Cho
DOI: 10.1145/2433396.2433470
发表时间: 2013-02
期刊: Proceedings of the sixth ACM international conference on Web search and data mining
影响因子: --
作者:
W. Feng;Jianyong Wang
通讯作者: W. Feng;Jianyong Wang
DOI: 10.1145/1367497.1367512
发表时间: 2008-04
期刊: --
影响因子: --
作者:
Qiaozhu Mei;Deng Cai;Duo Zhang;ChengXiang Zhai
通讯作者: Qiaozhu Mei;Deng Cai;Duo Zhang;ChengXiang Zhai
DOI: 10.1109/icde.2012.145
发表时间: 2012-04
期刊: 2012 IEEE 28th International Conference on Data Engineering
影响因子: --
作者:
Jiawei Han;Yizhou Sun;Xifeng Yan;Philip S. Yu
通讯作者: Jiawei Han;Yizhou Sun;Xifeng Yan;Philip S. Yu