期刊文献+

MPOPTM:一种基于热量模型的微博舆情预测模型

MPOPTM: A Microblog Public Opinion Prediction Model Based on Thermodynamic Model
下载PDF
导出
摘要 针对微博舆情发现领域的"冷启动"问题,提出一种基于热量模型的微博舆情预测模型(MPOPTM)。在该模型中,首先描述舆情检测中有关热量传播的介质定义,提出微博热量与热传导率的概念,建立微博與情预测模型。然后计算出每条微博在单位时间内增加的热量和热传导率,根据其改变量判断是否产生新的舆情。实验结果表明,MPOPTM能有效的检测出在微博中广为流传的微博舆情与刚刚产生地新舆情,克服现有技术中的"冷启动"问题。 According to the relationship between the medium and heat propagation velocity,presents a microblog public opinion prediction model based on thermodynamic model(MPOPTM).In MPOPTM,presents the concepts and formal definitions of medium,heat,thermal conductivi?ty in the public opinion prediction domain.Then the mathematical models of the thermodynamic for public opinion prediction are estab?lished.By using MPOPTM,the heat added and thermal conductivity of a post of microblog can be calculated quantitatively.Experiments on real dataset show that the performance of our method is better than traditional methods,and it is useful for predicting public opinion from microblog.
作者 谢凯 梁刚 杨文太 杨进 许春 XIE Kai;LIANG Gang;YANG Wen-tai;YANG Jin;XU Chun(College of Computer Science,Sichuan University,Chengdu 610065;College of Cyber Space Security,Sichuan University,Chengdu 610065)
出处 《现代计算机》 2018年第6期11-16,共6页 Modern Computer
基金 四川省教育厅重点资助科研项目(No.17ZA0238 No.17ZA0200) 四川省学术和技术带头人培养支持经费资助项目(No.2016)
关键词 與情 微博 热量模型 话题发现 Public Opinion Microblog Thermodynamic Model Topic Detection
  • 相关文献

参考文献3

二级参考文献32

  • 1洪宇,张宇,刘挺,李生.话题检测与跟踪的评测及研究综述[J].中文信息学报,2007,21(6):71-87. 被引量:153
  • 2Sakaki T. Okazaki M. Matsuo Y. Tweet analysis for real?time event detection and earthquake reporting system development[J]. IEEE Trans on Knowledge and Data Engineering. 2013: 25(4).919-931.
  • 3Hong Liangjie , Brian D. Empirical study of topic modeling in twitter[C]//Proc of SOMA'IO. New York: ACM. 2010: 80-88.
  • 4Diao Qiming. Jiang j ing , Zhu Feida , et al. Find bursty topic from micrcblogs[C]//PTOC of ACL'12. New York: ACM. 2012: 536-544.
  • 5Cui Anqi , Zhang Min. Liu Yiqun , et al. Discover breaking events with popular hash tags in twitter[C]//PTOC of CIKM'12. New York: ACM, 2012: 1794-1798.
  • 6Takahashi T. Tomioka R, Yarnanishi K. Discovering emerging topics in social streams via link anomaly detection[C]//Proc of ICDM'II. Piscataway. NJ: IEEE. 2011: 1230-1235.
  • 7Krishna Y, James C. Transient crowd discovery on the real?time social Web[C] I/Proc of WSDM'11. New York: ACM. 2011: 585-594.
  • 8Cataldi M, Caro L, Schifanella C. Emerging topic detection on twitter based on temporal and social terms evaluation[C] I/Proc of MDMKDD?10. New York: ACM, 2010: No.4.
  • 9Angel A, Koudas N. Sarkas N, et al, Dense subgraph maintenance under streaming edge weight updates for real?time story identification[C]//Proc of VLDB'12. New York: ACM. 2012: 574-585.
  • 10Agarwal M, Ramamritham K. Bhide M. Real time discovery of dense clusters in highly dynamic graphs: Identifying real world events in highly dynamic environments[C]//Proc of VLDB'12. New York: ACM, 2012: 980-991.

共引文献32

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部