期刊文献+

基于多分类的地震信息跟踪方法

Earthquake Information Tracking Based on the Multi-category Classification Method
下载PDF
导出
摘要 信息跟踪是指在文本数据流中检测与某个突发事件相关的信息,突发事件的动态演化特性是造成信息跟踪漏报率高的原因之一。为此,提出了基于多分类思想的突发事件信息跟踪方法,即将突发事件演化过程中出现的多个焦点看成是多个分类,而多个分类会在跟踪过程中动态调整。在该跟踪方法中,提出了基于上下文和潜在语义分析的帖子表示模型以及基于多焦点的突然事件表示模型。最后将本文提出的方法应用到某特定地震的信息跟踪系统中。实验结果表明,潜在语义分析针对性地解决了论坛草根性带来的用词多样性问题,而多焦点的话题模型在一定程度上弥补了话题的动态演化特性对跟踪系统性能的影响,基于多分类思想的突发事件信息跟踪方法使得系统的漏报率和误报率有了不同程度的降低,改善了地震信息跟踪系统的性能。 Information tracking is to detect the information related to a certain emergency from the text stream.The dynamic evolvement characteristic is one of the important reasons which lead to the high miss rate,and we propose an emergency information tracking method based on the multi-classification to deal with this problem,which regard the multi focuses appearing during the event evolvement as the multi classes.In this tracking method,we propose and explore a post representation model based on the context and latent semantic analysis and an event representation model based on the multi-focus.We apply the proposed information tracking method in the earthquake information,and the experimental results show that the proposed method can improve the performance of the earthquake information tracking system.
出处 《华北地震科学》 2015年第2期20-24,共5页 North China Earthquake Sciences
基金 地震科技星火计划项目(XH14017Y) 震情跟踪定向工作任务(2015010125)
关键词 突发事件 话题跟踪 多分类 动态演化 emergency information tracking multi-classification dynamic evolvement
  • 相关文献

参考文献16

  • 1刘晓亮.基于维基百科的军事舆情论坛话题追踪方法[J].计算机应用,2012,32(11):3026-3029. 被引量:3
  • 2席耀一,林琛,李弼程,周杰,许旭阳.基于语义相似度的论坛话题追踪方法[J].计算机应用,2011,31(1):93-96. 被引量:22
  • 3Kamaldeep Kaur, Vishal Gupta. A survey of Topic Tracking Techniques[J]. International Journal of Advanced Research in Computer Science and Software Engineering, 2012,5 (2) : 383-392. 被引量:1
  • 4Allan J, Papka R, Lavrenko V. On-Line new event detection and tracking[C]. Proc of the SIGIR'98, 1998:37-45. 被引量:1
  • 5Paraskevas Tsantarliotis, Evaggelia Pitoura. Topic Detection Using a Critical Term Graph on News-Related Tweets[C]. Proc of the ED- BT/ICDT 2015 Joint Conference, 2015:446-453. 被引量:1
  • 6Damiano Spina, Julio Gonzalo, Enrique Amigo. Learning Similarity Functions {ro Topic Detection in Online Reputation Monitoring[C]. Proc of SIGIR'14, Gold Coast, Queensland Australia, 2014 :150-167. 被引量:1
  • 7Tengfei Liu, Nevin L Zhang, Peixian Chen. Hierarchical Latent Tree Analysis for Topic Detection[C]. Proc of ECML PKDD 2014,Part II, LNCS 8725,2014:256-272. 被引量:1
  • 8Wenxu Long, Jixun Gao,Zhengtao Yu, et al. Online Chinese-Vietnamese Bilingual Topic Detection Based on RCRP Algorithm with E vent Elements[C]. Proc of C. Zong et al. (Eds.): NLPCC 2014, CCIS496,2014:422-429. 被引量:1
  • 9Feng A, Allan J. Finding and linking incidents in news[J]. Proc of the Conf on Information and Knowledge Management. Lisbon, 2007: 821-830. 被引量:1
  • 10王会珍,朱靖波,季铎,叶娜,张斌.基于反馈学习自适应的中文话题追踪[J].中文信息学报,2006,20(3):92-98. 被引量:17

二级参考文献71

  • 1贾自艳,何清,张海俊,李嘉佑,史忠植.一种基于动态进化模型的事件探测和追踪算法[J].计算机研究与发展,2004,41(7):1273-1280. 被引量:58
  • 2金珠,林鸿飞,赵晶.基于HowNet的话题跟踪及倾向性分类研究[J].情报学报,2005,24(5):555-561. 被引量:21
  • 3王会珍,朱靖波,季铎,叶娜,张斌.基于反馈学习自适应的中文话题追踪[J].中文信息学报,2006,20(3):92-98. 被引量:17
  • 4林鸿飞,宋丹,杨志豪.基于语义框架的话题追踪方法[C]//中国中文信息学会二十五周年学术会议.北京:清华大学出版社,2006:383-384. 被引量:1
  • 5The 2004 Topic Detection and Tracking(TDT2004)[S]. Task Definition and Evaluation Plan, Version 1.0, 2004. 被引量:1
  • 6Carbonell J, Yang Y, Lafferty J,et al. CMU Report on TDT-2: Segmentation, Detection and Tracking[ C] //Proceedings of the DARPA Broadcast News Transcription and Understanding Workshop. San Francisco: Morgan Kauffman, 1999: 117-120. 被引量:1
  • 7Schapire R E. BoosTexter: A Boosting-Based System for Text Categorization[J]. Machine Learning, 1999, 39(2/ 3): 135- 168. 被引量:1
  • 8Jianping Zeng, Shiyong Zhang. Incorporating Topic Transition in Topic Detection and Tracking Algorithms[J]. Expert Systems with Applications, 2009, 36(1) : 227 - 232. 被引量:1
  • 9Juha Makkonen, Helena Ahonen Myka, Marko Salmenkivi. Simple Semantics in Topic Detection and Tracking[J]. Information Retrieval, 2004,7 (3/4) : 347 - 368. 被引量:1
  • 10Liu Lu, Sun Lifeng. Web Video Topic Discovery and Tracking Via Bipartite Graph Reinforcement Model[C]// 2008:1009 - 1018. 被引量:1

共引文献65

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