基于词相关性特征的多归属谱聚类突发事件检测

doi:10.11959/j.issn.1000-436X.2020215

通信学报 ›› 2020, Vol. 41 ›› Issue (12): 193-204.doi: 10.11959/j.issn.1000-436X.2020215

基于词相关性特征的多归属谱聚类突发事件检测

蒋伟进¹^,²^,³^,⁴, 王扬¹^,², 刘晓亮²^,³, 吕斯健²^,³

¹ 湖南工商大学大数据与互联网创新研究院，湖南长沙 410205
² 新零售虚拟现实技术湖南省重点实验室，湖南长沙 410205
³ 湖南工商大学计算机与信息工程学院，湖南长沙 410205
⁴ 武汉理工大学计算机科学与技术学院，湖北武汉 430073

修回日期:2020-10-24 出版日期:2020-12-25 发布日期:2020-12-01
作者简介:蒋伟进（1967- ），男，湖南益阳人，博士，湖南工商大学教授、硕士生导师，主要研究方向为新一代分布式人工智能、软件定义物联网、社会计算、云计算与网络系统安全。
王扬（1996- ），女，湖南衡阳人，湖南工商大学硕士生，主要研究方向为社会计算、应急管理、复杂系统建模和仿真、大数据技术。
刘晓亮（1996- ），男，安徽阜阳人，湖南工商大学硕士生，主要研究方向为群智感知、移动计算、软件定义网络。
吕斯健（1996- ），男，广东深圳人，湖南工商大学硕士生，主要研究方向为移动群智感知、互信计算。
基金资助:
国家自然科学基金资助项目(61472136);国家自然科学基金资助项目(61772196);湖南省自然科学基金资助项目(2020JJ4249);湖南省社会科学基金重点资助项目(2016ZDB006);湖南省社会科学成果评审委员会课题重点基金资助项目(19ZD1005);湖南省学位与研究生教育改革研究基金资助项目(2020JGYB234);湖南省研究生科研创新资助项目(CX20201074)

Multi-attribute spectral clustering emergency detection based on word correlation feature

Weijin JIANG¹^,²^,³^,⁴, Yang WANG¹^,², Xiaoliang LIU²^,³, Sijian LYU²^,³

¹ Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha 410205, China
² Key Laboratory of Hunan Province for New Retail Virtual Reality Technology, Changsha 410205, China
³ College of Computer and Information Engineering, Hunan University of Technology and Business, Changsha 410205, China
⁴ School of Computer Science and Technology, Wuhan University of Technology, Wuhan 430073, China

Revised:2020-10-24 Online:2020-12-25 Published:2020-12-01
Supported by:
The National Natural Science Foundation of China(61472136);The National Natural Science Foundation of China(61772196);The Natural Science Founda-tion of Hunan Provincial(2020JJ4249);The Key Social Science Fund of Hunan Provincial(2016ZDB006);The Key Social Science Achievement Review Committee of Hunan Provincial(19ZD1005);The Degree and Graduate Education Reform Research Project of Hunan Provincial(2020JGYB234);Postgraduate Scientific Research Innovation Project of Hunan Province(CX20201074)

摘要/Abstract

摘要：

针对当前用于提取突发事件的方法存在精度低和效率低的问题，提出一种基于词相关性特征的突发事件检测方法，能从社会网络数据流中快速地检测出突发事件，以便相关的决策者可以及时有效地采取措施进行处理，使突发事件的负面影响被尽量降低，维护社会的安定。仿真结果表明，突发事件检测方法在实时博文数据流中具有很好的事件检测效果，与已有的方法相比，所提方法可以满足突发事件检测的需求，不仅能检测到子事件的详细信息，而且能准确地检测出事件的相关信息。

关键词: 突发事件, 单词关系图, 多归属谱聚类, 检测

Abstract:

For current methods for extracting emergencies had problems of low accuracy and low efficiency, an emergency detection method based on the characteristics of word correlation was proposed, which could quickly detect emergency events from the social network data stream, so that relevant decision makers could take timely and effective measures to deal with, making the negative impact of emergencies can be reduced as much as possible to maintain social stability.The simulation results show that the emergency event detection method has a better event detection effect in the real-time blog post data stream.Compared with the existing methods, the proposed method can meet the needs of emergency detection.Not only the detailed information of the sub-events can be detected, but also the related information of the events can be accurately detected.

Key words: emergency, word relationship graph, multi-attribute spectral clustering, detection

中图分类号:

TP393

蒋伟进, 王扬, 刘晓亮, 吕斯健. 基于词相关性特征的多归属谱聚类突发事件检测[J]. 通信学报, 2020, 41(12): 193-204.

Weijin JIANG, Yang WANG, Xiaoliang LIU, Sijian LYU. Multi-attribute spectral clustering emergency detection based on word correlation feature[J]. Journal on Communications, 2020, 41(12): 193-204.

图/表 14

图1

图2

表1

图3

图4

图5

图6

图7

图8

表2

图9

表3

图10

图11

参考文献 29

[30]	熊宇, 张一飞, 冯时 ,等. 基于多模态特征深度融合的微博流事件检测与跟踪[J]. 控制与决策, 2019,34(7): 1409-1416.
	XIONG Y , ZHANG Y F , FENG S ,et al. Microblog stream event detection and tracking based on deep fusion of multi-modal features[J]. Control and Decision, 2019,34(7): 1409-1416.
[31]	吴国华, 龚礼春, 袁理锋 ,等. 中文文本信息隐藏研究进展[J]. 通信学报, 2019,40(9): 145-156.
	WU G H , GONG L H , YUAN L F ,et al. Research progress on information hiding in Chinese text[J]. Journal on Communications, 2019,40(9): 145-156.
[32]	HU L , YU S , WU B ,et al. A neural model for joint event detection and prediction[J]. Neurocomputing, 2020,407: 376-384.
[33]	PEKAR V , BINNER J , NAJAFI H ,et al. Early detection of heterogeneous disaster events using social media[J]. Journal of the Association for Information Science and Technology, 2020,71(1): 43-54.
[34]	WANG Z H , GUO Y . Rumor events detection enhanced by encoding sentimental information into time series division and word representations[J]. Neurocomputing, 2020,397: 224-243.
[35]	郭磊, 李弼程, 赵军磊 . 基于主题词向量聚类的话题内新事件检测[J]. 中文信息学报, 2019,33(6): 64-71,79.
	GUO L , LI B C , ZHAO J L . New event detection within topic based on topic word vector clustering[J]. Journal of Chinese Information Processing, 2019,33(6): 64-71,79.
[36]	王凯, 洪宇, 邱盈盈 ,等. 融合上下文依赖和句子语义的事件线索检测研究[J]. 计算机科学与探索, 2018,12(3): 423-431.
	WANG K , HONG Y , QIU Y Y ,et al. Research on event clue detection combining context dependence and sentence semantics[J]. Journal of Computer Science and Exploration, 2018,12(3): 423-431.
[37]	代翔, 黄细凤, 唐瑞 ,等. 基于层次聚类的子话题检测算法[J]. 华南理工大学学报(自然科学版), 2019,47(8): 84-95.
[1]	LIU Y , PENG H , LI J ,et al. Event detection and evolution in multi-lingual social streams[J]. Frontiers of Computer Science, 2020,14(5): 1-15.
[2]	闻佳, 王宏君, 邓佳 ,等. 基于深度学习的异常事件检测[J]. 电子学报, 2020,48(2): 308-313.
[37]	DAI X , HUANG X F , TANG R ,et al. Subtopic detection algorithm based on hierarchical clustering[J]. Journal of South China University of Technology (Natural Science Edition), 2019,47(8): 84-95.
[38]	JANANI R , VIJAYARANI S . Text document clustering using spectral clustering algorithm with particle swarm optimization[J]. Expert Systems with Applications, 2019,134: 192-200.
[2]	WEN J , WANG H J , DENG J ,et al. Abnormal event detection based on deep learning[J]. Chinese Journal of Electronics, 2020,48(2): 308-313.
[3]	胡文斌, 王欢, 严丽平 ,等. 面向节点演化波动的社会网络事件检测方法[J]. 软件学报, 2017,28(10): 2693-2703.
	HU W B , WANG H , YAN L P ,et al. Social network event detection method for node evolution and fluctuation[J]. Journal of Software, 2017,28(10): 2693-2703.
[4]	MU L , JIN P , ZHENG L ,et al. Lifecycle-based event detection from microblogs[C]// Companion Proceedings of the The Web Conference 2018.[S.n.:s.l.], 2018: 283-290.
[5]	PRADHAN A K , MOHANTY H , LAL R P . Event detection and aspects in twitter:a bow approach[C]// International Conference on Distributed Computing and Internet Technology. Berlin:Springer, 2019: 194-211.
[6]	GOTO J , MIYAZAKI T , TAKEI Y ,et al. Automatictweet detection based on data specified through news production[C]// Proceedings of the 23rd International Conference on Intelligent User Interfaces Companion. New York:ACM Press, 2018:1.
[7]	周刚, 邹鸿程, 熊小兵 ,等. MB-SinglePass:基于组合相似度的微博话题检测[J]. 计算机科学, 2017,39(10): 198-202.
	ZHOU G , ZOU H C , XION X B ,et al. MB-SinglePass:microblog topic detection based on combined similarity[J]. Computer Science, 2017,39(10): 198-202.
[8]	QIU Y F , CHENG L B . Research onsudden topic detection method for microblog[J]. Computer Engineering, 2012,38(9): 288-290.
[9]	李莹莹, 马帅, 蒋浩谊 ,等. 一种基于社交事件关联的故事脉络生成方法[J]. 计算机研究与发展, 2018,55(9): 1972-1986.
	LI Y Y , MA S , JIANG H Y ,et al. A method for generating story context based on social event correlation[J]. Computer Research and Development, 2018,55(9): 1972-1986.
[10]	张婧丽, 周文瑄, 洪宇 ,等. 基于框架语义扩展训练集的有监督事件检测方法[J]. 中文信息学报, 2019,33(5): 82-92,131
	ZHANG J L , ZHOU W X , HONG Y ,et al. Supervised event detection method based on frame semantic extension training set[J]. Chinese Journal of Information, 2019,33(5): 82-92,131
[11]	陆垚杰, 林鸿宇, 韩先培 ,等. 基于语言学扰动的事件检测数据增强方法[J]. 中文信息学报, 2019,33(7): 110-117.
	LU Y J , LIN H Y , HAN X P ,et al. Incident detection data enhancement method based on linguistic disturbance[J]. Chinese Journal of Information, 2019,33(7): 110-117.
[12]	ZHU Z , LIANG J , LI D ,et al. Hot topic detection based on a refined TF-IDF algorithm[J]. IEEE Access, 2019,7: 26996-27007.
[13]	张鲁民, 贾焰, 周斌 ,等. 一种基于情感符号的在线突发事件检测方法[J]. 计算机学报, 2018,36(8): 1659-1667.
	ZHANG L M , JIA Y , ZHOU B ,et al. An online emergency detection method based on emotional symbols[J]. Chinese Journal of Computers, 2018,36(8): 1659-1667.
[14]	仲兆满, 管燕, 李存华 ,等. 微博网络地域 Top-k 突发事件检测[J]. 计算机学报, 2018,41(7): 1504-1516.
	ZHONG Z M , GUAN Y , LI C H ,et al. Detection of Top-k emergencies in Weibo networks[J]. Chinese Journal of Computers, 2018,41(7): 1504-1516.
[15]	KALDEN J P H , . Dataanalysis within the netherlands coast-guard:risk mapping,social network analysis and anomaly detection[C]// NL ARMS Netherlands Annual Review of Military Studies 2018. The Hague:TMC Asser Press, 2018: 193-200.
[16]	ZOU X M , YANG J , ZHANG J P . Sentiment-based and hashtag-based Chinese online bursty event detection[J]. Multimedia Tools and Applications, 2018,77(16): 21725-21750.
[17]	张仰森, 段宇翔, 王建 ,等. 基于多种词特征的微博突发事件检测方法[J]. 电子学报, 2019,47(9): 1919-1928.
	ZHANG Y S , DUAN Y X , WANG J ,et al. Microblog emergency detection method based on multiple word features[J]. Chinese Journal of Electronics, 2019,47(9): 1919-1928.
[18]	ZHANG Q , DU J , KOU F ,et al. Bursty topic detection based on bursty term detection and filtration[C]// Chinese Intelligent Systems Conference. Berlin:Springer, 2019: 211-219.
[19]	GUPTA A , LAMBA H , KUMARAGURU P ,et al. Faking Sandy:characterizing and identifying fake images on Twitter during Hurricane Sandy[C]// Proceedings of the 22nd International Conference on World Wide Web.[S.n.:s.l.], 2013: 729-736.
[20]	WANG Z H , GUO Y . Empower rumor events detection from Chinese microblogs with multi-type individual information[J]. Knowledge and Information Systems, 2020,62(2): 3585-3614.
[21]	赵海林 . 基于用户行为的推特事件检测方法研究[D]. 成都:电子科技大学, 2018.
	ZHAO H L . Research on twitter incident detection method based on user behavior[D]. Chengdu:University of Electronic Science and Technology of China, 2018.
[22]	介飞, 谢飞, 李磊 ,等. 社交网络中隐式事件突发性检测[J]. 自动化学报, 2018,44(4): 730-742.
	JIE F , XIE F , LI L ,et al. Implicit incident detection in social networks[J]. Acta Automatica Sinica, 2018,44(4): 730-742.
[23]	姚子瑜, 屠守中, 黄民烈 ,等. 一种半监督的中文垃圾微博过滤方法[J]. 中文信息学报, 2016,30(5): 176-186.
	YAO Z Y , TA S Z , HUANG M L ,et al. A semi-supervised Chinese junk microblog filtering method[J]. Chinese Information Processing, 2016,30(5): 176-186.
[24]	王勇, 肖诗斌, 郭跇秀 ,等. 中文微博突发事件检测研究[J]. 现代图书情报技术, 2018(2): 57-62.
	WANG Y , XIAO S B , GUO J X ,et al. Research on Chinese Weibo emergencies detection[J]. Modern Library and Information Technology, 2018(2): 57-62.
[25]	费绍栋, 杨玉珍, 刘培玉 ,等. 融合情感过滤的突发事件检测方法[J]. 计算机应用, 2015,35(5): 1320-1323.
	FEI S D , YANG Y Z , LIU P Y ,et al. Emergent incident detection method fused with emotion filtering[J]. Journal of Computer Applications, 2015,35(5): 1320-1323.
[26]	陈国兰 . 基于爆发词识别的微博突发事件监测方法研究[J]. 情报杂志, 2014(9): 123-128.
	CHEN G L . Research on Weibo emergencies monitoring method based on outbreak word recognition[J]. Journal of Information, 2014(9): 123-128.
[27]	郭跇秀, 吕学强, 李卓 . 基于突发词聚类的微博突发事件检测方法[J]. 计算机应用, 2014,34(2): 486-490,505.
	GUO J X , LYU X Q , LI Z . Microblog emergency detection method based on sudden word clustering[J]. Journal of Computer Applications, 2014,34(2): 486-490,505.
[28]	SHI J , MALIK J . Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22(8): 888-905.
[29]	ZHEN F R , MIAO D Q , ZHANG Z F ,et al. News topic detection approach on Chinese microblog[J]. Computer science, 2018,39(1): 138-141.

序号	字段名称	字段类型	描述
1	user_id	long	用户ID
2	user_name	string	用户昵称
3	content	string	微博内容
4	zan	Int	点赞数
5	zhuan	int	转发数
6	time	timestamp	发布时间

阈值	Precision	Recall	F1
0.5	88.92%	77.23%	81.94%
0.6	84.98%	82.24%	84.02%
0.7	82.57%	87.95%	85.11%
0.8	75.1%	90.07%	82.01%
0.9	63.33%	90.12%	73.99%

编号	子图单词数量	单词重合率
1	9	1.0
2	9	0.95
3	10	0.9
4	11	0.85
5	10	0.9
6	9	0.8
7	8	0.85

基于词相关性特征的多归属谱聚类突发事件检测

Multi-attribute spectral clustering emergency detection based on word correlation feature

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 29

相关文章 15

Metrics

推荐阅读 0

[1]	郑金志, 汲如意, 张立波, 赵琛. 基于Transformer解码的端到端场景文本检测与识别算法[J]. 通信学报, 2023, 44(5): 64-78.
[2]	苏新, 张桂福, 行鸿彦, Zenghui Wang. 基于平衡生成对抗网络的海洋气象传感网入侵检测研究[J]. 通信学报, 2023, 44(4): 124-136.
[3]	戴千一, 张斌, 郭松, 徐开勇. 基于多分类器集成的区块链网络层异常流量检测方法[J]. 通信学报, 2023, 44(3): 66-80.
[4]	孙贺麟, 高洪元, 杜亚男, 程建华, 刘亚鹏. 频控阵MIMO雷达的目标数与方位参数联合估计方法[J]. 通信学报, 2023, 44(2): 41-51.
[5]	霍纬纲, 梁锐, 李永华. 基于随机Transformer的多维时间序列异常检测模型[J]. 通信学报, 2023, 44(2): 94-103.
[6]	杨宏宇, 杨海云, 张良, 成翔. 基于特征依赖图的源代码漏洞检测方法[J]. 通信学报, 2023, 44(1): 103-117.
[7]	刘延华, 李嘉琪, 欧振贵, 高晓玲, 刘西蒙, MENG Weizhi, 刘宝旭. 对抗训练驱动的恶意代码检测增强方法[J]. 通信学报, 2022, 43(9): 169-180.
[8]	袁程胜, 郭强, 付章杰. 基于差分隐私的深度伪造指纹检测模型版权保护算法[J]. 通信学报, 2022, 43(9): 181-193.
[9]	蒋锐, 李俊, 徐友云, 王小明, 李大鹏. 基于联邦卡尔曼滤波器的容错GPS-AOA-SINS组合导航算法[J]. 通信学报, 2022, 43(8): 78-89.
[10]	陈炜宇, 骆俊杉, 王方刚, 丁海洋, 王世练, 夏国江. 无线隐蔽通信容量限与实现技术综述[J]. 通信学报, 2022, 43(8): 203-218.
[11]	朱政宇, 林宇, 王梓晅, 巩克现, 陈鹏飞, 王忠勇, 梁静. 基于MeanShift的短波跳频信号快速盲检测[J]. 通信学报, 2022, 43(6): 200-210.
[12]	廖建新, 付霄元, 戚琦, 王敬宇, 孙海峰. 6G-ADM：基于知识空间的6G网络管控体系[J]. 通信学报, 2022, 43(6): 3-15.
[13]	卢东旭, 周娴, 刘飞, 霍佳皓, 苑金辉, 隆克平. 高线宽容忍度的高谱效SSB-PAM-DD方案[J]. 通信学报, 2022, 43(5): 36-44.
[14]	廖育荣, 王海宁, 林存宝, 李阳, 方宇强, 倪淑燕. 基于深度学习的光学遥感图像目标检测研究进展[J]. 通信学报, 2022, 43(5): 190-203.
[15]	李凤华, 李超洋, 郭超, 李子孚, 房梁, 郭云川. 泛在网络环境下隐蔽通道关键技术研究综述[J]. 通信学报, 2022, 43(4): 186-201.