分布式环境下话题发现算法性能分析  

Performance analysis of topic detection algorithms in distributed environment

作　　者：邓璐[1] 贾焰[1] 方滨兴[2] 周斌[1] 张涛 刘心 DENG Lu;JIA Yan;FANG Binxing;ZHOU Bin;ZHANG Tao;LIU Xin(College of Computer,National University of Defense Technology,Changsha 410073,China;College of Computer,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]国防科技大学计算机学院,湖南长沙410073 [2]北京邮电大学计算机学院,北京100876

出　　处：《通信学报》2018年第8期176-184,共9页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61502517;No.61472433;No.61732004;No.61732022);国家重点研发计划课题基金资助项目(No.0708068118002;No.2017YFB0803303)~~

摘　　要：社交网络成为现在人们生活的一种重要方式,越来越多的人选择通过社交网络表达观点、抒发心情。在海量的数据下,快速发现讨论的内容得到越来越多的研究者的关注,随即出现了大量的话题发现算法。在大规模新浪微博数据环境下,针对3种经典分布式话题发现算法,结合社交网络平台的特点提出了分析性能的测试方案,并根据测试方案比较与分析了3种算法的性能,指出了各算法的优缺点,为后续应用提供参考。Social network has become a way of life,therefore more and more people choose social network to express their views and feelings.Quickly find what people are talking about in big data gets more and more attention.And a lot of related methods of topic detection spring up in this situation.The performance analysis project was proposed based on the characteristics of social network.According to the project,the performances of some typical topic detection algorithms were tested and compared in large-scale data of Sina Weibo.What’s more,the advantages and disadvantages of these algorithms were pointed out so as to provide references for later applications.

关 键 词：话题发现 分布式环境 社交网络 性能分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]