|本期目录/Table of Contents|

[1]牛飞,钟少波,刘楠,等.一种改进的灾害新闻3要素提取方法研究*[J].中国安全生产科学技术,2023,19(2):13-19.[doi:10.11731/j.issn.1673-193x.2023.02.002]
　NIU Fei,ZHONG Shaobo,LIU Nan,et al.Research on an improved extraction method for three elements of disaster news[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(2):13-19.[doi:10.11731/j.issn.1673-193x.2023.02.002]
点击复制

一种改进的灾害新闻3要素提取方法研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年2期
页码:
13-19
栏目:
学术论著
出版日期:
2023-02-28

文章信息/Info

Title:
Research on an improved extraction method for three elements of disaster news
文章编号:
1673-193X(2023)-02-0013-07
作者:
牛飞; 钟少波; 刘楠; 钟伟齐; 杨德威; 叶欣澜; 梅新
(1.湖北大学 资源环境学院，湖北 武汉 430062；
2.北京市科学技术研究院 城市系统工程研究所，北京 100035；
3.首都师范大学 资源环境与旅游学院，北京 100048）
Author(s):
NIU Fei;  ZHONG Shaobo;  LIU Nan;  ZHONG Weiqi;  YANG Dewei;  YE Xinlan;  MEI Xin
(1.Faculty of Resources and Environment,Hubei University,Wuhan Hubei 430062,China;
2.Institute of Urban Systems Engineering,Beijing Academy of Science and Technology,Beijing 100035,China;
3.College of Resource Environment and Tourism,Capital Normal University,Beijing 100048,China)
关键词:
灾害新闻; 灾害新闻3要素; 自然语言处理; 目标分类; 命名实体识别
Keywords:
disaster news;  three elements of disaster news;  natural language processing (NLP);  object classification;  named entity recognition (NER)
分类号:
X915.5
DOI:
10.11731/j.issn.1673-193x.2023.02.002
文献标志码:
A
摘要:
为提取灾害性新闻中的基本要素，迅速掌握灾害事件信息和发展趋势，将目标分类和命名实体识别（named entity recognition，NER）相结合，提出改进的灾害新闻3要素提取方法。构建滑动窗检测器搭载不同的分类模型，实现对新闻文本的灾害主题识别与时空位置要素范围判定，结合命名实体识别完成对时空位置要素的精准提取，并以灾害事故信息文本为例进行测试。研究结果表明：通过在火灾、地震和滑坡新闻中进行数据集中测试，发现本文方法相较于LSTM，BILSTM，BILSTM-CRF提取效果更优；本文方法可对大量灾害性新闻的灾害3要素进行识别提取，对灾害信息进行时空规律分析，研究结果可在灾害应急响应中发挥重要作用。
Abstract:
In order to quickly grasp the information and development trend of disaster events,combined the extraction of basic elements of disaster news with the research of object classification and named entity recognition (NER),an improved extraction method for three elements of disaster news was proposed.Asliding window detector was constructed to carry different classification models,which achieved to recognize the disaster topic and determine the scope of spatio-temporal location elements of the news text,and then completed the accurate extraction of spatio-temporal location elements combined with NER.The test was carried out by taking the disaster accident information text as an example.The results showed that compared with LSTM,BILSTM and BILSTM-CRF methods,the F1 value of the proposed method increased by 18.6%,7.5% and 0.8%,respectively.The method could quickly recognize and extract the disaster three elements of a large number of disastrous news,so as to analyze the spatio-temporal law of disaster information.The research results can play an important role in the disaster emergency response.

参考文献/References:

［1］张楠，邵卫卫.应急管理部发布2021年全国自然灾害基本情况［J］.中国减灾,2022(3):7.
［2］DAVID A.World disasters report 2005:focus on information in disasters［J］.Disasters,2006,30(3):377-379.
［3］REGALADO R V J,CHUA J L,CO J L,et al.Adaptive information extraction of disaster information from twitter［C］//2014 International Conference on Advanced Computer Science and Information System，IEEE,2014:286-289.
［4］贾平,张云霞,刘克俭.提升综合应急装备水平增强应急决策信息保障能力—灾害现场信息获取技术研究与应用示范获得国家重点研发计划支持［J］.中国减灾,2016(21):30-31. JIA Ping,ZHANG Yunxia,LIU Kejian.Improve the level of comprehensive emergency equipment,enhance the ability of emergency decision- making information support-research and application demonstration of disaster site information acquisition technology has won the support of national key research and development plans［J］.Disaster Reduction in China,2016(21):30-31.
［5］王红斌,王健雄,张亚飞,等.主题不平衡新闻文本数据集的主题识别方法研究［J］.数据分析与知识发现,2021,5(3):109-120. WANG Hongbin,WANG Jianxiong,ZHANG Yafei,et al.Topic recognition of news reports with imbalanced contents［J］.Data Analysis and Knowledge Discovery,2021,5(3):109-120.
［6］安璐,李倩.基于热点主题识别的突发事件次生衍生事件探测［J］.情报资料工作,2020,41(6):24-35. AN Lu,LI Qian.A probe into secondary derived events of emergencies cased on hot topic recognition［J］.Information and Documentation Services,2020,41(6):24-35.
［7］TLLEZ V A,MONTES Y，GMEZ M,et al.Using machine learning for extracting information from natural disaster news reports［J］.Computacióny Sistemas,2009,13(1):33-44.
［8］刘淑涵,王艳东,付小康.利用卷积神经网络提取微博中的暴雨灾害信息［J］.地球信息科学学报,2019,21(7):1009-1017. LIU Shuhan,WANG Yandong,FU Xiaokang.Extracting rainstorm disaster information from microblogs using convolutional neural network［J］.Journal of Geoinformation Science,2019,21(7):1009-1017.
［9］吴建华,胡烈云,赵宇,等.基于BILSTM-CRF与分类分层标注的微博中突发事件时空信息精细识别方法［J］.地理与地理信息科学,2021,37(3):1-8. WU Jianhua,HU Lieyun,ZHAO Yu,et al.Method of finely identifying spatio-temporal information of emergencies from weibo based on BiLSTM-CRF and classified-hierarchical annotation［J］.Geography and Geo-information Science,2021,37(3):1-8.
［10］宋敦江,杨霖,钟少波.基于BERT的灾害三元组信息抽取优化研究［J］.中国安全科学学报,2022,32(2):115-120. SONG Dunjiang,YANG Lin,ZHONG Shaobo.Research on optimization of disaster triplet information extraction based on BERT［J］.China Safety Science Journal,2022,32(2):115-120.
［11］曾庆田,胡晓慧,李超.融合主题词嵌入和网络结构分析的主题关键词提取方法［J］.数据分析与知识发现,2019,3(7):52-60. ZENG Qingtian,HU Xiaohui,LI Chao.Extracting keywords with topic embedding and network structure analysis［J］.Data Analysis and Knowledge Discovery,2019,3(7):52-60.
［12］HOCHREITER S,SCHMIDHUBER J.Long short-term memory［J］.Neural Computation,1997,9(8):1735-1780.
［13］付剑锋.面向事件的知识处理研究［D］.上海：上海大学,2010.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期： 2022-07-04
* 基金项目： 国家自然科学基金项目(72174031)；北京市科学技术研究院北科青年学者计划项目(YS202004)
作者简介： 牛飞，硕士研究生，主要研究方向为灾害信息提取、自然语言处理。
通信作者： 梅新，博士，教授，主要研究方向为数字乡村和智慧城市治理、大数据空间可视化。
更新日期/Last Update: 2023-03-07