社交媒体中的谣言识别研究综述  

A Survey on Rumor Identification over Social Media

作　　者：刘雅辉 靳小龙[1,2,3] 沈华伟[1,2,3] 鲍鹏 程学旗[1,2,3] LIU Ya-Hui;JIN Xiao-Long;SHEN Hua-Wei;BAO Peng;HENG Xue-Qi(CAS Key Laboratory of Network Data Sciencean Technology,Beijing 100190;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190;School of Computer and Control Engineering,University of Chinese Academy of Sciences,Beijing 100049;Shihezi University,Shihezi,Xinjiang 832003;School of Software Engineering,Beijing Jiaotong University,Beijing 100044)

机构地区：[1]中国科学院网络数据科学与技术重点实验室,北京100190 [2]中国科学院计算技术研究所,北京100190 [3]中国科学院大学计算机与控制学院,北京100049 [4]石河子大学,新疆石河子832003 [5]北京交通大学软件学院,北京100044

出　　处：《计算机学报》2018年第7期1536-1558,共23页Chinese Journal of Computers

基　　金：国家重点研究发展计划(2016YFB1000902);国家重点基础研究发展计划(2013CB329602);国家自然科学基金(61572473;61472400;61232010);中国科学院青年创新促进会优秀会员项目;CCF腾讯犀牛鸟基金项目(20160107);中央高校基本科研专项资金(2015rc031)资助~~

摘　　要：近年来,社交媒体蓬勃发展,Facebook、Twitter、新浪微博、微信等逐渐成为人们获取或分享信息的重要渠道.这种人人可以参与信息发布和传播的方式在给人们的信息共享提供极大便利的同时,也带来一些突出的问题,特别是网络谣言的不断滋生和快速传播,给社交媒体的有效利用和科学管理提出了严峻挑战.因此,如何快速准确地识别谣言是个重要的研究问题,也是抑制谣言传播、降低谣言危害的前提.该文对社交媒体上的谣言识别工作进行综述,首先介绍了谣言研究的发展历程以及分类;然后,介绍了影响谣言识别的关键要素、当前谣言识别的主要方法;最后,对社交媒体中谣言识别存在的问题与发展趋势进行了总结和展望.In recent years,the popularization of Web 2.0 technology spurs the flourish of social media.There emerged a few globally influential social media platforms,such as Facebook,Twitter,Sina Weibo,and WeChat,which have gradually become a very important channel for people to obtain or share information.On social media,everyone can participate in publishing and disseminating information.According to the 39th Statistical Report on Internet Development in China released by China Internet Network Information Center(CNNIC),as of December 2016,China’s Internet users reached 731 million,and the Internet penetration rate was 53.2%.The social media platform makes people more closely connected,and has broken the original six degrees separation,now less than five degrees.The way of information dissemination has undergone enormous changes.Especially,the microblogging system has a strong network effect with the optimization of information flow products,the outbreak of video and the steady progress of the vertical.Active users continue to maintain high-speed growth.By the end of 2016,the monthly active users of Sina Weibo increased to 313 million.Similarly,Twitter also had 319 million daily active users.CNNIC data show that Sina Weibo in the general social applications ranked second,accounting for 43.5%.73.9%of users focus on news or hot topics via Sina Weibo,which means that Sina Weibo has become a public platform,and the main channel for people to understand the current hot information.However,as a side-effect of social media,rumors,commonly defined as unconfirmed and uncertain information posted intentionally or unintentionally by some users,are also widely propagated over social media,which may lead to significant negative effects and even severe social problems,e.g.,social panic and even chaos.For example,a hacker released a fake tweet about explosions in the White House through the official Twitter account of the Associated Press(AP)on April 23,2013.This rumor was widely reposted and caused an immediate social panic:S&P 500

关 键 词：谣言 社交媒体 谣言识别 谣言传播 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]