微博用户转发行为预测是微博社交网络消息扩散模型构建的基础，在舆情监控、市场营销与政治选举等领域有着广泛的应用.为了提高用户转发行为预测的精度，本文在MRF（Markov Random Field）能量优化框架下综合分析了用户属性与微博内容特征、用户转发行为约束、群体转发先验等因素对用户转发行为的影响，并在逻辑回归模型的基础上构造了相应的能量函数对用户转发行为进行了全局性的预测.实验结果表明，微博用户转发行为不仅取决于用户属性、微博内容等特征，而且也受到用户转发行为约束、群体转发先验等因素不同程度的影响.相对于传统算法，本文算法可以更准确地对用户转发行为进行建模，因而可获得更好的预测结果.
Abstract
Predicting user retweet behaviors is the basis of building the information diffusion model in micorblog social networks,and also is applied for a variety of fields such as public opinion monitoring,viral marketing,political campaign etc.In order to improve the accuracy of predicting user retweet behaviors,under the MRF (Markov Random Field) framework,the paper comprehensively analyzes the effects caused by user attributes,microblog contents,the constraints between user retweet behaviors and the group retweet priors,and constructs the corresponding energy function based on the logistic regression model to globally predict user retweet behaviors.Experimental results show user retweet behaviors not only depend on user attributes,and micorblog contents,but also are influenced by the constraints between user retweet behaviors and the group retweet priors in varying degrees.Compared to the traditional methods,our proposed method can accurately model user retweet behaviors and thus achieve satisfactory results.
关键词
新浪微博 /
转发预测 /
能量优化 /
逻辑回归
{{custom_keyword}} /
Key words
sina microblog /
retweet predicting /
energy optimization /
logistic regression
{{custom_keyword}} /
中图分类号：
TP391
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Pezzoni F,An J,Passarella A,Crowcroft J,Conti M.Why do I retweet it? an information propagation model for microblogs[A].Proceedings of the 5th International Conference on Social Informatics[C].Kyoto,Japan:Springer,2013.360-369.
[2] Yang J,Leskovec J.Modeling information diffusion in implicit networks[A].IEEE International Conference on Data Mining[C].Sydney,Australian:IEEE Press,2010.599-608.
[3] Huang D,Zhou J,Yang F,Qin M,Mu D.Understanding retweeting behaviors in twitter[J].Journal of Computational Information Systems,2015,11(13):4625-4634.
[4] Suh B,Hong L,Pirolli P,Chi E H.Want to be retweeted? large scale analytics on factors impacting retweet in twitter network[A].IEEE International Conference on Privacy,Security,Risk and Trust[C].Minneapolis,USA:IEEE Press,2010.177-184.
[5] 曹玖新,吴江林,石伟,刘波,郑啸,罗军舟.新浪微博网信息传播分析与预测[J].计算机学报,2014(4):779-790. CAO Jiu-xin,WU Jiang-lin,SHI Wei,LIU Bo,ZHENG Xiao,LUO Jun-zhou.Sina microblog information diffusion analysis and prediction[J].Chinese Journal of Computers,2014(4):779-790.(in Chinese)
[6] 张旸,路荣,杨青.微博客中转发行为的预测研究[J].中文信息学报,2012,26(4):109-114. ZHANG Yang,LU Rong,YANG Qing.Predicting retweeting in microblogs[J].Journal of Chinese Information Processing,2012,26(4):109-114.
[7] Hong L,Dan O,Davison B D.Predicting popular messages in twitter[A].International Conference on World Wide Web[C].Hyderabad,India:ACM Press,2011.57-58.
[8] Tang X,Miao Q,Quan Y,Tang J,Deng K.Predicting individual retweet behavior by user similarity:a multi-Task learning approach[J].Knowledge-Based Systems,2015,89(C):681-688.
[9] Xu Z,Zhang Y,Wu Y,Yang Q.Modeling user posting behavior on social media[A].International ACM SIGIR Conference on Research and Development in Information Retrieval[C].Portland,USA:ACM Press,2012.545-554.
[10] Yang Z,Guo J,Cai K,Tang J,Li J,Zhang L,Su Z.Understanding retweeting behaviors in social networks[A].ACM International Conference on Information and Knowledge Management[C].Toronto,Canada:ACM Press,2010.1633-1636.
[11] 周沧琦,赵千川,卢文博.基于兴趣变化的微博用户转发行为建模[J].清华大学学报:自然科学版,2015,55(11):1163-1170. ZHOU Cang-qi,ZHAO Qian-chuan,LU Wen-bo.Modeling of the forwarding behavior in microblogging with adaptive interest[J].Journal of Tsinghua University (Science and Technology),2015,55(11):1163-1170.(in Chinese)
[12] Peng H K,Zhu J,Piao D,Yan R,Zhang Y.Retweet modeling using conditional random fields[A].International Conference on Data Mining Workshops[C].Vancouver,Canada:IEEE Press,2011.336-343.
[13] Zhang J,Tang J,Li J,Liu Y,Xing C.Who influenced you? predicting retweet via social influence locality[J].Acm Transactions on Knowledge Discovery from Data,2015,9(3):1-26.
[14] Wang Z,Chen E,Liu Q,Yang Y,Ge Y,Chang B.Maximizing the coverage of information propagation in social networks[A].International Conference on Artificial Intelligence[C],Buenos,Argentina:AAAI Press,2015.2104-2110.
[15] Koller D,Friedman N.Probabilistic Graphical Models-Principles and Techniques[M].Cambridge,USA:The MIT Press,2009.
[16] Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3:993-1022.
[17] Kohli P,Ladick ý L,Torr P H S.Robust higher order potentials for enforcing label consistency[J].International Journal of Computer Vision,2009,82(3):302-324.
[18] Newman M E J.Fast algorithm for detecting community structure in networks[J].Physical Review E Statistical Nonlinear & Soft Matter Physics,2004,69(6):066133-066133.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金 (No.U1404620，No.U1404622）; 河南省自然科学基金 (No.162300410347）; 河南省科技攻关项目 (No.172102310727，No.162102310589，No.162102210396，No.162102310590）; 河南省高校重点科研项目 (No.17A520018，No.17A520019，No.15A520116，No.16B520034，No.16A520105）; 周口师范学院高层次人才科研启动基金 (No.zknuc2015103）
{{custom_fund}}
PDF(722 KB)
