摘要
微博快速转发的特点使得在微博传播的过程中存在着显著的时间特性。本文对这种时间特性进行分析,挖掘传播规律,对传播规律建模,并对未来的微博传播情况进行预测。本文从微博整体的角度上考虑时间特性,通过分类和回归模型,对微博传播的趋势加以判定,并对传播数量加以预测。本文获取Twitter的505万条微博数据,利用TREC公布的相关性标注,验证了方法的有效性。在预测微博未来涨跌判定的实验中,准确率达到了80%,而预测相关微博数量的实验中,准确率在50%以上。
引文
[1]Suh B,Hong L,Pirolli P,et al.Want to be Retweeted?Large Scale Analytics on Factors Impacting Retweet in Twitter Network[C]//IEEE Second International Conference on Social Computing.IEEE,2010:177-184.
[2]Phuvipadawat S,Murata T.Breaking News Detection and Tracking in Twitter[C]//Ieee/wic/acm International Conference on Web Intelligence and Intelligent Agent Technology.IEEE Computer Society,2010:120-123.
[3]Cao J X,Wu J L,Shi W,et al.Sina microblog information diffusion analysis and prediction[J].Chinese Journal of Computers,2014.
[4]Zaman T R,Herbrich R,Gael J V,et al.Predicting Information Spreading in Twitter[J].Computational Social Science&the Wisdom of Crowds Workshop,2010.
[5]Weng J,Lim E P,Jiang J,et al.TwitterRank:finding topic-sensitive influential twitterers[J].2010:261-270.
[6]Pal A,Counts S.Identifyingtopical authoyities in microblogs[C].Proc of the 4th ACM Int Conf on Web Search and Data M ining(WSD'11),New York:ACM,2011:45-54.
[7]刘功申,孟魁,谢婧.一种微博预警算法[J].计算机科学,2014,41(12):33-37.
[8]Zhang Y,Rong L U,Yang Q.Predicting Retweeting in Microblogs[J].Journal of Chinese Information Processing,2012,26(4):109-108.
[9]Yang Z,Guo J,Cai K,et al.Understanding retweeting behaviors in social networks[C]//ACM International Conference on Information and Knowledge Management.ACM,2010:1633-1636.
[10]Yang Zi.Predictive models in social network analysis[M].S.dissertation].Tsinghua University,Beijing,2011.
[11]HI.boyd,danah,Golder,Scott,and Lotan,Gilad.Tweet Tweet Retweet:Conversational Aspects of Retweeting on Twitter.[C]//2010.
[12]Yang Z,Guo J,Cai K,et al.Understanding retweeting behaviors in social networks[C]//ACM International Conference on Information and Knowledge Management.ACM,2010:1633-1636.
[13]Kossinets G,Kleinberg J,Watts D.The structure of information pathways in a social communication network[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2008:435-443.
[14]Zhou Tao,Fu Zhong-Qian,Niu Yong-Wei,et al.Research on spreading dynamics on complex networks.Progress in Natural Science,2005,15(5):513-518.
[15]Fan P,Li P,Jiang Z,et al.Measurement and analysis of topology and information propagation on SinaMicroblog[C]//IEEE International Conference on Intelligence and Security Informatics.IEEE,2011:396-401.
[16]Cha M,Mislove A,Adams B,et al.Characterizing social cascades in flickr[C]//The Workshop on Online Social Networks.ACM,2008:13-18.
[17]Leskovec J,Mcglohon M,Faloutsos C,et al.Cascading Behavior in Large Blog Graphs[J].Sdm,20 07,15(1):9:3-9:56.
[18]Wu F,Huberman B A,Adamic L A,et al.Information flow in social groups[J].Physica A Statistical Mechanics&Its Applications,2004,337(1-2):327-335.
[19]Szabo G,Huberman B A.Predicting the popularity of online content[M].ACM,2010.
[20]Liben-Nowell D,Kleinberg J.Tracing information flow on a global scale using Internet chain-letter data[J].Proceedings of the National Academy of Sciences of the United States of America,2008,105(12):4633.
[21]Galuba W,Aberer K,Chakraborty D,et al.Outtweeting the twitterers-predicting information cascades in microblogs[C]//Wonference on Online Social Networks.USENIX Association,2010.
[22]周志华,王珏.机器学习及其应用[M].北京:清华大学出版社,2007.