Article(id=1149741821347148180, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, articleNumber=1003-3033(2024)01-0053-09, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.01.0741, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1692115200000, receivedDateStr=2023-08-16, revisedDate=1700841600000, revisedDateStr=2023-11-25, acceptedDate=null, acceptedDateStr=null, onlineDate=1752049411378, onlineDateStr=2025-07-09, pubDate=1706371200000, pubDateStr=2024-01-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752049411378, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752049411378, creator=13701087609, updateTime=1752049411378, updator=13701087609, issue=Issue{id=1149741815273800564, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='1', pageStart='1', pageEnd='252', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752049409931, creator=13701087609, updateTime=1756468937446, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1168278657316430156, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1168278657316430157, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=53, endPage=61, ext={EN=ArticleExt(id=1149741821636555158, articleId=1149741821347148180, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Intelligent modeling and simulation of online public opinion for major accidents based on proactive safety, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

In case of major security accidents,information disseminated wantonly and difficult to discern in terms of authenticity can easily cause negative social sentiments. This poses several issues to emergency rescue. Sentiment analysis,topic calculation,and the SEIR model were used to investigate online opinion simulation and control strategies for major security accidents. The CDBN-TCN-CRF sentiment analysis model was proposed by coupling the Convolutional Deep Belief Networks (CDBN),temporal convolutional networks (TCN),and conditional random fields (CRF). Then,the T-distributed Wasserstein autoencoder (TWAE) topic computation model was used to discern sentiment polarity,topic categories,race sentiment trajectory,and public attention focal points within the network discourse. Furthermore,the proposed SEIR model was used to predict online public opinion tendency and analyze the dissemination dynamics and their influencing factors. The results indicate that the coupling of CDBN-TCN-CRF sentiment analysis,TWAE topic computation,and SEIR model has a better prediction performance on network discourse analysis and trend analysis.

, correspAuthors=Kefan XIE, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Xin CHEN, Kefan XIE), CN=ArticleExt(id=1149741838849978470, articleId=1149741821347148180, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于主动安全的重大事故网络舆情智能建模与仿真, columnId=1149733271296193071, journalTitle=中国安全科学学报, columnName=安全社会科学与安全管理, runingTitle=null, highlight=null, articleAbstract=

针对重大安全事故发生时,肆意传播且真伪难辨的信息易引起社会负面情绪,给应急处置及救援工作带来不便的问题,基于主动安全理念,结合情感分析模型、主题计算模型和易感人群-潜伏人群-感染人群-离去人群(SEIR)模型,开展重大安全事故网络舆情仿真及控制策略研究。运用卷积深度置信网络(CDBN)、时域卷积网络(TCN)、条件随机场(CRF)组成的CDBN-TCN-CRF情感分析模型及T分布瓦瑟斯坦自编码器(TWAE)主题计算模型,识别情感极性及主题类别,跟踪网络舆情情感倾向及民众关注热点;运用SEIR模型来预测网络舆情走势,并研究网络舆情的传播过程和影响因素。结果表明:CDBN-TCN-CRF情感分析模型、TWAE主题计算模型及SEIR模型结合使用,可以更好地展现其对网络舆情深度分析与趋势预测的能力。

, correspAuthors=谢科范, authorNote=null, correspAuthorsNote=
**谢科范(1963—),男,湖南益阳人,博士,二级教授,主要从事安全科学理论、安全生产管理、安全系统和风险管理等方面的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=TzXptmS5gEWqzqp9gz7UJg==, magXml=+6ZrcasEmQfoWYxSSc+/Qw==, pdfUrl=null, pdf=hWDT2W43FTM7abio1id2IA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VGjyHolmFzn8Gp/WiHCYXg==, mapNumber=null, authorCompany=null, fund=null, authors=

陈 鑫 (1986—),男,辽宁盘锦人,博士,助理研究员,主要从事风险管理、人工智能、自然语言处理等方面的研究。E-mail:

谢科范,教授

, authorsList=陈鑫, 谢科范)}, authors=[Author(id=1172172189999682424, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=470821800@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172172190062596986, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, authorId=1172172189999682424, language=EN, stringName=Xin CHEN, firstName=Xin, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172172190112928635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, authorId=1172172189999682424, language=CN, stringName=陈鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=武汉理工大学 管理学院,湖北 武汉 430070, bio={"img":"mDmMfqHOjNk4XR0NlpI1OA==","content":"

陈 鑫 (1986—),男,辽宁盘锦人,博士,助理研究员,主要从事风险管理、人工智能、自然语言处理等方面的研究。E-mail:

"}, bioImg=mDmMfqHOjNk4XR0NlpI1OA==, bioContent=

陈 鑫 (1986—),男,辽宁盘锦人,博士,助理研究员,主要从事风险管理、人工智能、自然语言处理等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172172189924184948, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, xref=null, ext=[AuthorCompanyExt(id=1172172189928379253, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China), AuthorCompanyExt(id=1172172189936767862, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=武汉理工大学 管理学院,湖北 武汉 430070)])]), Author(id=1172172190175843197, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xkf@whut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1172172190335226751, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, authorId=1172172190175843197, language=EN, stringName=Kefan XIE, firstName=Kefan, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, address=School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172172190414918528, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, authorId=1172172190175843197, language=CN, stringName=谢科范, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, address=武汉理工大学 管理学院,湖北 武汉 430070, bio={"content":"

谢科范,教授

"}, bioImg=null, bioContent=

谢科范,教授

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172172189924184948, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, xref=null, ext=[AuthorCompanyExt(id=1172172189928379253, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China), AuthorCompanyExt(id=1172172189936767862, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=武汉理工大学 管理学院,湖北 武汉 430070)])])], keywords=[Keyword(id=1172172190528164737, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, orderNo=1, keyword=proactive safety), Keyword(id=1172172190591079298, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, orderNo=2, keyword=major accident), Keyword(id=1172172190641410947, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, orderNo=3, keyword=online public opinion analysis), Keyword(id=1172172190695936900, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, orderNo=4, keyword=susceptible-exposed-infectious-removed (SEIR) model), Keyword(id=1172172190758851461, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, orderNo=5, keyword=sentiment analysis), Keyword(id=1172172190809183110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, orderNo=1, keyword=主动安全), Keyword(id=1172172190859514759, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, orderNo=2, keyword=重大事故), Keyword(id=1172172190926623624, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, orderNo=3, keyword=网络舆情分析), Keyword(id=1172172191006315401, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, orderNo=4, keyword=易感人群-潜伏人群-感染人群-离去人群(SEIR)模型), Keyword(id=1172172191060841354, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, orderNo=5, keyword=情感分析)], refs=[Reference(id=1172172192398824349, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2023, volume=8, issue=3, pageStart=2062, pageEnd=2076, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=WANG Cong, WANG Zhenpo, ZHANG Zhiqiang, journalName=IEEE Transactions on Intelligent Vehicles, refType=null, unstructuredReference=WANG Cong, WANG Zhenpo, ZHANG Zhiqiang, et al. Integrated post-impact planning and active safety control for autonomous vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(3): 2062-2076., articleTitle=Integrated post-impact planning and active safety control for autonomous vehicles, refAbstract=null), Reference(id=1172172192453350302, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=ALDIANSYAH M R, SASONGKO P S, journalName=3rd International Conference on Informatics and Computational Sciences, refType=null, unstructuredReference=ALDIANSYAH M R, SASONGKO P S. Twitter sentiment analysis about public opinion on 4G smartfren network services using convolutional neural network[C]. 3rd International Conference on Informatics and Computational Sciences, 2019: 1-6., articleTitle=Twitter sentiment analysis about public opinion on 4G smartfren network services using convolutional neural network, refAbstract=null), Reference(id=1172172192533042079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=5, pageStart=546, pageEnd=553, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=刘定一, 沈阳阳, 詹天明, journalName=江苏大学学报, refType=null, unstructuredReference=刘定一, 沈阳阳, 詹天明, 等. 融合微博热点分析和LSTM模型的网络舆情预测方法[J]. 江苏大学学报, 2021, 42(5): 546-553., articleTitle=融合微博热点分析和LSTM模型的网络舆情预测方法, refAbstract=null), Reference(id=1172172192595956640, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=5, pageStart=546, pageEnd=553, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=LIU Dingyi, SHEN Yangyang, ZHAN Tianming, journalName=Journal of Jiangsu University, refType=null, unstructuredReference=LIU Dingyi, SHEN Yangyang, ZHAN Tianming, et al. Network public opinion forecasting method fusing microblog hotspot analysis and LSTM model[J]. Journal of Jiangsu University, 2021, 42(5): 546-553., articleTitle=Network public opinion forecasting method fusing microblog hotspot analysis and LSTM model, refAbstract=null), Reference(id=1172172192671454113, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=YAN Chun, LIU Jiahui, LIU Wei, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=YAN Chun, LIU Jiahui, LIU Wei, et al. Research on public opinion sentiment classification based on attention parallel dual-channel deep learning hybrid model[J]. Engineering Applications of Artificial Intelligence, 2022,116:DOI:10.1016/j.engappai.2022.105448., articleTitle=Research on public opinion sentiment classification based on attention parallel dual-channel deep learning hybrid model, refAbstract=null), Reference(id=1172172192734368674, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=250, pageEnd=252, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=ZHANG Linghan, journalName=2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering, refType=null, unstructuredReference=ZHANG Linghan. Design of early warning mechanism of network public opinion using deep learning[C]. 2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering, 2022: 250-252., articleTitle=Design of early warning mechanism of network public opinion using deep learning, refAbstract=null), Reference(id=1172172192793088931, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=272, pageEnd=276, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=ZHANG Baosheng, HUANG He, journalName=2020 International Conference on Information Science and Education, refType=null, unstructuredReference=ZHANG Baosheng, HUANG He. Research on evolution and control of network public opinion based on SEIR model with martial law mechanism[C]. 2020 International Conference on Information Science and Education, 2020: 272-276., articleTitle=Research on evolution and control of network public opinion based on SEIR model with martial law mechanism, refAbstract=null), Reference(id=1172172192885363620, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1495, pageEnd=1500, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=JIANG Changbin, ZHANG Yaoyuan, WANG Hu, journalName=2020 IEEE International Conference on Big Data and Cloud Computing, refType=null, unstructuredReference=JIANG Changbin, ZHANG Yaoyuan, WANG Hu, et al. Study on coupled social network public opinion communication based on improved SEIR[C]. 2020 IEEE International Conference on Big Data and Cloud Computing, 2020: 1495-1500., articleTitle=Study on coupled social network public opinion communication based on improved SEIR, refAbstract=null), Reference(id=1172172192969249701, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=90, pageEnd=103, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=RAFFAELE D, PATRICIA D, GIUSEPPE G, journalName=International Conference on Computational Science and Its Applications, refType=null, unstructuredReference=RAFFAELE D, PATRICIA D, GIUSEPPE G, et al. A modified SEIR model: stiffness analysis and application to the diffusion of fake news[C]. International Conference on Computational Science and Its Applications, 2022: 90-103., articleTitle=A modified SEIR model: stiffness analysis and application to the diffusion of fake news, refAbstract=null), Reference(id=1172172193032164262, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=GENG Lixiao, YANG Shuran, WANG Ke, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=GENG Lixiao, YANG Shuran, WANG Ke, et al. Modeling public opinion dissemination in a multilayer network with SEIR model based on real social networks[J]. Engineering Applications of Artificial Intelligence, 2023,125:DOI:10.1016/j.engappai.2023.106719., articleTitle=Modeling public opinion dissemination in a multilayer network with SEIR model based on real social networks, refAbstract=null), Reference(id=1172172193086690215, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2011, volume=54, issue=10, pageStart=95, pageEnd=103, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=LEE H, GROSSE R, RANGANATH R, journalName=Communications of the ACM, refType=null, unstructuredReference=LEE H, GROSSE R, RANGANATH R, et al. Unsupervised learning of hierarchical representations with convolutional deep belief networks[J]. Communications of the ACM, 2011, 54(10): 95-103., articleTitle=Unsupervised learning of hierarchical representations with convolutional deep belief networks, refAbstract=null), Reference(id=1172172193157993384, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=47, pageEnd=54, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=LEA C, VIDAL R, REITER A, journalName=European Conference on Computer Vision, refType=null, unstructuredReference=LEA C, VIDAL R, REITER A, et al. Temporal convolutional networks: a unified approach to action segmentation[C]. European Conference on Computer Vision, 2016: 47-54., articleTitle=Temporal convolutional networks: a unified approach to action segmentation, refAbstract=null), Reference(id=1172172193225102249, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=16, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=TOLSTIKHIN I, BOUSQUET O, GELLY S, journalName=6th International Conference on Learning Representations(ICLR 2018), refType=null, unstructuredReference=TOLSTIKHIN I, BOUSQUET O, GELLY S, et al. Wasserstein auto-encoders[C]. 6th International Conference on Learning Representations(ICLR 2018), 2018: 1-16., articleTitle=Wasserstein auto-encoders, refAbstract=null), Reference(id=1172172193288016810, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=10, pageStart=114, pageEnd=126, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=方匡南, 任蕊, 朱建平, journalName=管理科学学报, refType=null, unstructuredReference=方匡南, 任蕊, 朱建平, 等. 基于动态SEIR模型的传染性疾病预测和政策评估[J]. 管理科学学报, 2022, 25(10): 114-126., articleTitle=基于动态SEIR模型的传染性疾病预测和政策评估, refAbstract=null), Reference(id=1172172193350931371, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=10, pageStart=114, pageEnd=126, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=FANG Kuangnan, REN Rui, ZHU Jianping, journalName=Journal of Management Sciences in China, refType=null, unstructuredReference=FANG Kuangnan, REN Rui, ZHU Jianping, et al. Prediction and policy assessment of infectious diseases transmission using dynamic SEIR model[J]. Journal of Management Sciences in China, 2022, 25(10): 114-126., articleTitle=Prediction and policy assessment of infectious diseases transmission using dynamic SEIR model, refAbstract=null), Reference(id=1172172193409651628, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=刘丽华, journalName=自然灾害微博舆情的社会计算模型建构研究, refType=null, unstructuredReference=刘丽华. 自然灾害微博舆情的社会计算模型建构研究[D]. 武汉: 武汉大学, 2018., articleTitle=null, refAbstract=null), Reference(id=1172172193476760493, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=LIU Lihua, journalName=Research on social computing model construction of natural disasters weibo public opinion based on sentiment analysis and topic modeling, refType=null, unstructuredReference=LIU Lihua. Research on social computing model construction of natural disasters weibo public opinion based on sentiment analysis and topic modeling[D]. Wuhan: Wuhan University, 2018., articleTitle=null, refAbstract=null), Reference(id=1172172193552257966, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=竺佳芳, journalName=顾及时空主题特征的分布式灾害舆情信息获取与分析方法研究, refType=null, unstructuredReference=竺佳芳. 顾及时空主题特征的分布式灾害舆情信息获取与分析方法研究[D]. 杭州: 浙江大学, 2019., articleTitle=null, refAbstract=null), Reference(id=1172172193615172527, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=ZHU Jiafang, journalName=Distributed acquisition and analysis methods of disaster-related public opinions based on spatiotemporal and theme features, refType=null, unstructuredReference=ZHU Jiafang. Distributed acquisition and analysis methods of disaster-related public opinions based on spatiotemporal and theme features[D]. Zhejiang: Zhejiang University, 2019., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1172172189924184948, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, xref=null, ext=[AuthorCompanyExt(id=1172172189928379253, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China), AuthorCompanyExt(id=1172172189936767862, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, companyId=1172172189924184948, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=武汉理工大学 管理学院,湖北 武汉 430070)])], figs=[ArticleFig(id=1172172191211836299, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.1, caption=Sentiment analysis model framework based on CDBN-TCN-CRF, figureFileSmall=B96S8zOYlJONUvlwdcyFdQ==, figureFileBig=y+Vm09M5Kz40iZcFm+X0/w==, tableContent=null), ArticleFig(id=1172172191262167948, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图1, caption=基于CDBN-TCN-CRF的情感分析模型架构, figureFileSmall=B96S8zOYlJONUvlwdcyFdQ==, figureFileBig=y+Vm09M5Kz40iZcFm+X0/w==, tableContent=null), ArticleFig(id=1172172191320888205, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.2, caption=TWAE topic model flowchart, figureFileSmall=sLa7uz5dM9gnNyYM80ZLfw==, figureFileBig=QjABrW/Ccbrp7f5P20hluw==, tableContent=null), ArticleFig(id=1172172191392191374, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图2, caption=TWAE主题模型架构, figureFileSmall=sLa7uz5dM9gnNyYM80ZLfw==, figureFileBig=QjABrW/Ccbrp7f5P20hluw==, tableContent=null), ArticleFig(id=1172172191450911631, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.3, caption=Statistical analysis for the sentiment value of online public opinion, figureFileSmall=jXecoE6rdpftmkzrK6LjgQ==, figureFileBig=OLF3mjJPBvNgPK5t46OTKw==, tableContent=null), ArticleFig(id=1172172191522214800, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图3, caption=网络舆情情感值分析统计, figureFileSmall=jXecoE6rdpftmkzrK6LjgQ==, figureFileBig=OLF3mjJPBvNgPK5t46OTKw==, tableContent=null), ArticleFig(id=1172172191589323665, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.4, caption=Online public opinion analysis model, figureFileSmall=DMHkZ/pUpHVUP8vY2RRAPA==, figureFileBig=l/+SQcKeaWl2T2CGZE7Kxw==, tableContent=null), ArticleFig(id=1172172191664821138, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图4, caption=网络舆情分析模型, figureFileSmall=DMHkZ/pUpHVUP8vY2RRAPA==, figureFileBig=l/+SQcKeaWl2T2CGZE7Kxw==, tableContent=null), ArticleFig(id=1172172191736124307, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.5, caption=Effects of infection rate on dissemination trends of online public opinion, figureFileSmall=kjwUNi9PGw9ZB4C4xHTwJw==, figureFileBig=xEHHdn2Ych7b5yMNbcKG4Q==, tableContent=null), ArticleFig(id=1172172191790650260, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图5, caption=传染率对网络舆情传播趋势的影响, figureFileSmall=kjwUNi9PGw9ZB4C4xHTwJw==, figureFileBig=xEHHdn2Ych7b5yMNbcKG4Q==, tableContent=null), ArticleFig(id=1172172191845176213, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.6, caption=Effects of activity rate on dissemination trends of online public opinion, figureFileSmall=ex2Rp5QYY0026SL0Ekj6Rw==, figureFileBig=0uXKaGiLxuF1N56PJX+JUQ==, tableContent=null), ArticleFig(id=1172172191895507862, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图6, caption=活跃率对网络舆情传播趋势的影响, figureFileSmall=ex2Rp5QYY0026SL0Ekj6Rw==, figureFileBig=0uXKaGiLxuF1N56PJX+JUQ==, tableContent=null), ArticleFig(id=1172172191950033815, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Fig.7, caption=Effects of recovery rate on dissemination trends of online public opinion, figureFileSmall=KZE4ZuQY5lbpLuZ9w2I3wA==, figureFileBig=xY1R7LOSWAMpusw4N1Rqpg==, tableContent=null), ArticleFig(id=1172172192000365464, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=图7, caption=退出率对网络舆情传播趋势的影响, figureFileSmall=KZE4ZuQY5lbpLuZ9w2I3wA==, figureFileBig=xY1R7LOSWAMpusw4N1Rqpg==, tableContent=null), ArticleFig(id=1172172192059085721, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Tab.1, caption=

Topic generation results in "8·12 explosion"

, figureFileSmall=null, figureFileBig=null, tableContent=
主题 关键词
主题1 天津 爆炸 天津港 炸药 危险品 安全 事故
主题2 遇难 火灾 瑞海 消防 公司 能量 消防员
主题3 天津 爆炸 火灾 响应 网友 机场 回家
主题4 天津 交通 爆炸 学校 照料 停课 关注
主题5 天津港 酒店 服务 安全 滞留 物资 部署
主题6 逆行 爆炸区 消防 居民区 仓库 危险品 滨海
主题7 安全 居家 爆炸 火灾 烧伤 消防 浓烟
主题8 天津港 睡觉 居民 爆炸 爆发 周边 火灾
主题9 爆炸 滞留 婴儿 公安 天津 帮助 救援
主题10 缺乏 事故 重大 安全 物资 消防 厂区
主题11 天津 爆炸 突发 滨海 事故 防火 浓烟
主题12 滨海 爆炸 应急 消防 报道 中国 媒体
主题13 危害 爆炸 火灾 爆炸区 食物 居家 消防
主题14 天津 火灾 天津港 瘫痪 交通 直播 记录
主题15 天津港 救援 伤员 烫伤 防护 维修 躲避
), ArticleFig(id=1172172192138777498, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=表1, caption=

“8·12爆炸”主题生成结果

, figureFileSmall=null, figureFileBig=null, tableContent=
主题 关键词
主题1 天津 爆炸 天津港 炸药 危险品 安全 事故
主题2 遇难 火灾 瑞海 消防 公司 能量 消防员
主题3 天津 爆炸 火灾 响应 网友 机场 回家
主题4 天津 交通 爆炸 学校 照料 停课 关注
主题5 天津港 酒店 服务 安全 滞留 物资 部署
主题6 逆行 爆炸区 消防 居民区 仓库 危险品 滨海
主题7 安全 居家 爆炸 火灾 烧伤 消防 浓烟
主题8 天津港 睡觉 居民 爆炸 爆发 周边 火灾
主题9 爆炸 滞留 婴儿 公安 天津 帮助 救援
主题10 缺乏 事故 重大 安全 物资 消防 厂区
主题11 天津 爆炸 突发 滨海 事故 防火 浓烟
主题12 滨海 爆炸 应急 消防 报道 中国 媒体
主题13 危害 爆炸 火灾 爆炸区 食物 居家 消防
主题14 天津 火灾 天津港 瘫痪 交通 直播 记录
主题15 天津港 救援 伤员 烫伤 防护 维修 躲避
), ArticleFig(id=1172172192205886363, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=EN, label=Tab.2, caption=

Comparisons between simulations of TWAE+SVM model and those of other models

, figureFileSmall=null, figureFileBig=null, tableContent=
分类模型 精确率(Precidion) 召回率(Recall) F1
LDA+SVM 0.74 0.79 0.78
VAE+SVM 0.82 0.83 0.85
WAE+SVM 0.89 0.84 0.87
TWAE+SVM 0.92 0.94 0.95
), ArticleFig(id=1172172192277189532, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741821347148180, language=CN, label=表2, caption=

TWAE+SVM与其他模型对比结果

, figureFileSmall=null, figureFileBig=null, tableContent=
分类模型 精确率(Precidion) 召回率(Recall) F1
LDA+SVM 0.74 0.79 0.78
VAE+SVM 0.82 0.83 0.85
WAE+SVM 0.89 0.84 0.87
TWAE+SVM 0.92 0.94 0.95
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.01.0741, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.01.0741, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.01.0741, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.01.0741, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于主动安全的重大事故网络舆情智能建模与仿真
收藏切换
PDF下载
陈鑫 , 谢科范 **
中国安全科学学报 | 安全社会科学与安全管理 2024,34(1): 53-61
收起
收藏切换
中国安全科学学报 | 安全社会科学与安全管理 2024, 34(1): 53-61
基于主动安全的重大事故网络舆情智能建模与仿真
全屏
陈鑫 , 谢科范**
作者信息
  • 武汉理工大学 管理学院,湖北 武汉 430070
  • 陈 鑫 (1986—),男,辽宁盘锦人,博士,助理研究员,主要从事风险管理、人工智能、自然语言处理等方面的研究。E-mail:

    谢科范,教授

通讯作者:

**谢科范(1963—),男,湖南益阳人,博士,二级教授,主要从事安全科学理论、安全生产管理、安全系统和风险管理等方面的研究。E-mail:
Intelligent modeling and simulation of online public opinion for major accidents based on proactive safety
Xin CHEN , Kefan XIE**
Affiliations
  • School of Management,Wuhan University of Technology,Wuhan Hubei 430070,China
出版时间: 2024-01-28 doi: 10.16265/j.cnki.issn1003-3033.2024.01.0741
文章导航
收藏切换

针对重大安全事故发生时,肆意传播且真伪难辨的信息易引起社会负面情绪,给应急处置及救援工作带来不便的问题,基于主动安全理念,结合情感分析模型、主题计算模型和易感人群-潜伏人群-感染人群-离去人群(SEIR)模型,开展重大安全事故网络舆情仿真及控制策略研究。运用卷积深度置信网络(CDBN)、时域卷积网络(TCN)、条件随机场(CRF)组成的CDBN-TCN-CRF情感分析模型及T分布瓦瑟斯坦自编码器(TWAE)主题计算模型,识别情感极性及主题类别,跟踪网络舆情情感倾向及民众关注热点;运用SEIR模型来预测网络舆情走势,并研究网络舆情的传播过程和影响因素。结果表明:CDBN-TCN-CRF情感分析模型、TWAE主题计算模型及SEIR模型结合使用,可以更好地展现其对网络舆情深度分析与趋势预测的能力。

主动安全  /  重大事故  /  网络舆情分析  /  易感人群-潜伏人群-感染人群-离去人群(SEIR)模型  /  情感分析

In case of major security accidents,information disseminated wantonly and difficult to discern in terms of authenticity can easily cause negative social sentiments. This poses several issues to emergency rescue. Sentiment analysis,topic calculation,and the SEIR model were used to investigate online opinion simulation and control strategies for major security accidents. The CDBN-TCN-CRF sentiment analysis model was proposed by coupling the Convolutional Deep Belief Networks (CDBN),temporal convolutional networks (TCN),and conditional random fields (CRF). Then,the T-distributed Wasserstein autoencoder (TWAE) topic computation model was used to discern sentiment polarity,topic categories,race sentiment trajectory,and public attention focal points within the network discourse. Furthermore,the proposed SEIR model was used to predict online public opinion tendency and analyze the dissemination dynamics and their influencing factors. The results indicate that the coupling of CDBN-TCN-CRF sentiment analysis,TWAE topic computation,and SEIR model has a better prediction performance on network discourse analysis and trend analysis.

proactive safety  /  major accident  /  online public opinion analysis  /  susceptible-exposed-infectious-removed (SEIR) model  /  sentiment analysis
陈鑫, 谢科范. 基于主动安全的重大事故网络舆情智能建模与仿真. 中国安全科学学报, 2024 , 34 (1) : 53 -61 . DOI: 10.16265/j.cnki.issn1003-3033.2024.01.0741
Xin CHEN, Kefan XIE. Intelligent modeling and simulation of online public opinion for major accidents based on proactive safety[J]. China Safety Science Journal, 2024 , 34 (1) : 53 -61 . DOI: 10.16265/j.cnki.issn1003-3033.2024.01.0741
在新安全格局下,重大安全事故(简称重大事故)网络舆情的控制与管理需要做到关口前移和事前防范,以实现风险的主动管控,保障重大事故的应急处置工作免受不当舆情干扰;而做到这一点,需树立主动安全理念,运用主动安全策略和主动安全技术。主动安全理念强调在事故发生后,负面网络舆情出现前,采取积极主动的预防措施,全面、深入地分析和应对事故相关的网络舆情信息。主动安全策略是在主动安全理念下制定的具体措施和方法。主动安全技术是实现主动安全理念和策略的关键[1]
目前,国内外网络舆情研究主要基于人工智能及易感人群-潜伏人群-感染人群-离去人群(Susceptible-Exposed-Infectious-Removed,SEIR)模型等相关技术开展。关于人工智能方面,ALDIANSYAH等[2]通过词嵌入维度、卷积层激活函数、最大池化窗口大小等参数组合来寻找面向舆情情感分类表现最佳的卷积神经网络。刘定一等[3]提出长短时记忆网络及微博热点分析的融合方法,用于解决社交媒体对舆情走势影响较大的问题。闫春等[4]提出双向长短时记忆网络和卷积神经网络的混合模型,用来提取文本情感特征并识别词语歧义。张凌寒等[5]利用大数据分析网络舆情预警系统的需求,实现了基于深度学习框架的设计。关于SEIR模型方面,张宝生等[6]基于SEIR传染病动力学模型,预测和评估突发公共事件中舆情的演变,建立了考虑隔离机制的舆情演变过程模型。江长斌等[7]通过设置特定的节点连接方式和网络耦合率,构建双层耦合社交网络,同时改进了SEIR模型来模拟网络中的舆情传播过程。RAFFAELE等[8]提出一种SEIR改进模型,运用常微分方程,给出相关参数的定义,并通过局部线性化系统,计算雅各布矩阵最大和最小特征值的实部之比。耿立校等[9]基于复杂网络理论构建了多层网络,通过改进的 SEIR 模型模拟了多层网络中的信息传输趋势。
目前,关于安全事故网络舆情的研究缺少一种系统性的网络舆情分析方法。鉴于此,笔者拟以主动安全理念为基础,提出卷积深度置信网络(Conditional Deep Belief Network,CDBN)、时域卷积网络(Temporal Convolutional Network,TCN)、条件随机场(Conditional Random Field,CRF)组成的情感分析模型CDBN-TCN-CRF及主题计算模型T分布瓦瑟斯坦自编码器(T-Distribution Wasserstein Auto-Encoder,TWAE),追踪网络舆情情感倾向及民众关注热点,为SEIR模型提供数据的输入、验证和补充,结合SEIR模型来预测网络舆情走势,并研究网络舆情的传播过程和影响因素,以期提高应对重大事故的效率和准确性。
基于人工智能技术和SEIR模型的网络舆情分析,在研究网络舆情事件传播和社会反应时可以相互补充和支持。通过将两者结合使用,可更全面地了解网络舆情走势,评估干预措施效果,为最终决策提供科学依据。
当事故灾害发生时,人们通常通过微博来获取实时灾情和相关救援情况,并发表个人主观的观点和情绪。故采用微博数据集作为数据源,开展基于人工智能的事故灾害网络舆情分析。
对于微博文本语料库中的文本数据存在重复内容多、口语化高、表情及标点多的特点,无法直接分析网络舆情,需先清洗语料数据,以提高网络舆情分析处理的效果和结果准确性。微博网络舆情文本预处理的步骤:①去除重复及低频词语。②采用Jieba分词器完成文本分词。③将这部分表情符号转义为带有明显情绪的词语,扩充语料库的多元性。④去除停用词。⑤通过Count Vectorize实现文本向量化。
传统的基于词袋模型的情感分类方法无法考虑单词之间的顺序和上下文信息,因此效果较差,而基于序列标注模型的情感分类方法则可有效解决此问题。因此,基于序列标注理念,结合CDBN[10] 、TCN[11]、CRF提出CDBN-TCN-CRF混合模型,实现输入端S1、S2、S3、S4、S5、S6等多个微博句子到输出端网络舆情情感标签负向、中性、正向的映射,模型架构如图1所示。
该模型的优势主要包括以下几个方面:①强大的特征提取能力。CDBN模型在学习过程中可以自动提取高级抽象特征,而TCN模型则可以有效地处理时序数据。这些特征的结合可以更准确地表达情感信息。② 上下文建模。引入TCN模型,能够捕捉到不同单词之间的关联关系,进而更好地理解情感的变化。③ 集成标签依赖关系。通过引入CRF模型,可以利用标签之间的依赖关系来提高情感分类的准确性,从而更好地处理文本中的标签推理和分类问题。
通过对网络舆情数据主题分类,可帮助分析者了解用户对特定主题的关注度、态度分布以及不同主题之间的关联性,从而更好地理解和预测舆情走向和发展。瓦瑟斯坦自编码器(Wasserstein Auto-Encoder,WAE)是一种用于学习数据分布和进行数据生成的新算法[12]。该方法应用在自然语言处理领域,展现了不错的研究价值。但是,WAE模型直接应用在网络舆情分析过程中,存在着不同类型文本数据的适应性问题,因此,结合T分布改进和优化WAE模型,提出TWAE模型,其架构如图2所示。
TWAE是一种改进的自编码器模型,x是计算概率密度的变量,z为隐变量,该模型引入T分布作为潜在表示的先验分布,与高斯分布相比,T分布对离群点更不敏感,因此,具有更强的鲁棒性。在计算置信区间时,通过计算T分布的概率密度,以确定这个差异是否足够大。T分布的概率密度函数见下式:
f ( x ) = 1 / ( s · 2 π ) · ( 1 + ( x - m ) 2 / s 2 ) ( - ( n - 1 ) / 2 ) / Γ ( ( n - 1 ) / 2 )
式中:s为标准差,它是一个尺度参数,影响分布的宽度;m为均值,表示中心趋势;n为自由度,它是决定分布形状的参数;Γ是伽马函数,它用于分布的标准化。
TWAE模型的优化目标由2部分构成:一是重构误差,二是隐空间中的变分后验分布QWAE(z|x)与先验分布之间的差异。优化目标是使后验的边际分布PG(x|z)趋近先验分布,从而使得各输入样本在隐空间中能够合理地分布,在避免分布层叠题的同时,提升对不同文本类型的适用性。
SEIR模型是一种流行病学模型,常用于研究疾病的传播和控制[13]。在该模型中,将人群状态分为4类:易感者S、潜伏者E、感染者I和离去者R,这 4种人群之间可以相互转移。SE的转移、EI的转移、IR的转移、R数量、人口总数及感染峰值计算方法见下式:
d S / d t = - β S I / N
d E / d t = β S I / N - α E
d I / d t = α E - γ I
d R / d t = γ I
N = S + E + I + R
t _ p e a k = l n ( β / ( γ · S ) )
式中:t为时间;β为传染率,表示SI之间接触率和信息传播的速度,决定IS的传染效率;α为感染率,表示E转变为I的速率,决定潜伏者成为感染者概率;γ为离去率,表示感染者I转变为离去者R的速率,决定感染者恢复的概率;N为人口总数;t_peak 表示感染峰值的时间点。
针对重大事故网络舆情的分析,将4类人群重新定义如下:①易感者S'。是指还没有接触到该热点话题的人,他们还没有对该话题形成认知,也没有参与讨论,一旦他们接触到该话题,就会进入潜伏者状态。②潜伏者E'。是指已经接触到该话题但还未参与讨论的人,他们已经对该话题有一定的认知,但还没有做出明确的表态或参与讨论,一旦他们开始参与讨论,就会进入感染者状态。③活跃者(感染者)I',是指已经参与讨论该话题的活跃人群,他们在社交网络中转发、评论、点赞等行为可以促进热点话题的传播,感染者的传播能力和传播范围会影响热点话题的传播速度和范围;此时,α'称为活跃率。④退出者(离去者)R'。是指曾经参与讨论该话题但不再参与的人,他们对该话题已经失去了兴趣或者已经得出了自己的结论,退出者不会再对该话题产生影响,但是他们的观点和评论可能会影响其他人的看法和决策;此时,γ'称为退出率。此外,感染峰值的时间点t_peak在此处重新定义为舆情峰值t_peak',来计算舆情到达峰值的时间。
利用Python爬虫技术采集天津“8·12爆炸”事件相关微博。2015-08-12日T22:51:46,天津爆炸事件发生,当日23:00微博舆情初步爆发,进入13:00 时,微博讨论数量减少,在13日早9:00微博讨论量开始出现回升,在13日19:00达到峰值。总体来说,2015年8月13日微博讨论量最多,随后讨论量逐日递减,在事件发生后第7天,即8月18日讨论量出现小高峰。在8月27日,事故有关责任人被立案调查,相关微博数量再次出现一个小高峰。
网络舆情情感值代表了在网络上关于某个特定话题、事件或文本内容产生的情感倾向的数值化表示[14]。结合文中提出的CDBN-TCN-CRF模型计算情感值,根据CRF模型的输出结果,可以获得一系列离散的情感标签,表示文本序列中每个位置的情感类别。将CRF模型的输出标签作为输入特征,通过线性回归,实现了离散情感标签向连续情感值的映射。以8月13日为例,选取22 171条微博进入情感分析。具体统计结果如图3所示。统计结果表明:情感两级性特点明显,超过40%的微博展现了极端正面情绪,大约20%的微博展现了极端负面的情绪,总体来说,正向情绪在情感分布占据主导,但仍需要重点关注负向情绪的演进趋势,以便根据状态变化结果调整相应的应对策略。
运用TWAE主题模型计算得出2015天津“8·12 爆炸”语料库中最为核心的15个主题及每个主题中权重最高的7个关键词,主题生成结果见表1
支持向量机(Support Vector Machines,SVM)是非常典型的分类模型[15]。运用其继续对以上主题分类,方便开展主题的聚合性分析。为进一步判别文中提出方法TWAE+SVM网络舆情分析模型的有效性,引入潜在狄利克雷分布(Latent Dirichlet Allocation,LDA)、变分自编码器(Variational Auto-encoder,VAE)进行对比,搭建LDA+SVM,VAE+SVM,WAE+SVM,TWAE+SVM 4种试验情景。分类精度、召回率及F1值呈现在表2中。通过表2可知:文中提出的方法TWAE+SVM模型展现了更好的主题分类性能。
结合实际数据和参数进行推演,运用SEIR模型研究天津“8·12爆炸”事件网络舆情的传播过程和影响因素。通过数据获取与情况调研,天津“8·12爆炸”事件微博网络舆情影响人数高达百万,在爆炸发生20 h后网络舆情达到峰值,由于此事件网络传播迅速,一经发布呈指数倍传播发酵,且事件传播活跃度高,受网络舆情影响的民众不易从悲痛惋惜中恢复。将天津“8·12爆炸”事件微博网络舆情发展趋势与SEIR传染病模型相拟合,其参数取值为:总人数N=1 000 000,传染率β=2,活跃率α'=0.75,退出率γ'=0.1,网络舆情分析模型如图4所示。
传染率表示信息在舆情传播中的传播速度和传播范围,它受很多因素影响,包括信息的内容、传播途径、受众特征等。它表示每个感染者每天平均能够传播给多少个易感者,传染率大于1表示每个感染者平均能够传播给多于一个易感者,这也意味着信息的传播速度较快,且范围较泛。
当总人数N=1 000 000、活跃率α'=0.75、退出率γ'=0.1时,传染率β分别取0.25、0.5、1、2时,易感者、潜伏者、活跃者和退出者趋势变化如图5所示。
β=0.25时,每个感染者平均能够传播给1/4个易感者,舆情峰值在121h后到来,此时具备舆情传染性的活跃者人数达205 299人,舆情在190h后基本消退;当β=0.5时,每个感染者平均能够传播给1/2个易感者,舆情峰值在57h后到来,此时具备舆情传染性的活跃者人数达415 910人,舆情在110h后基本消退;当β=1时,每个感染者平均能够传播给一个易感者,舆情峰值在32 h后到来,此时具备舆情传染性的活跃者人数达571 737人,舆情在85 h后基本消退;当β=2时,每个感染者平均能够传播给2个易感者,舆情峰值在20 h后到来,此时具备舆情传染性的活跃者人数达661 328人,舆情在75 h后消退。
由此可知:传染率越高,舆情峰值到来越快,峰值时活跃者人数越多,舆情消退也越快。所以,当某重大事故的网络舆情快速传播,无法控制时,将此舆情的传染率在短时内提升,可较快消退舆情。
活跃率是指在给定时间段内,处于传播状态的信息数量占整个信息网络的比例。活跃率越低表示信息传播越慢,仅有少数信息在网络中传播;活跃率越高表示信息传播越广泛,大部分信息在网络中传播;活跃率极限接近于1表示信息传播达到最高点,整个网络中的所有信息均在传播。
若设置总人数N=1 000 000,传染率β=2,退出率γ'=0.1,活跃率α'分别取0.25、0.5、0.75、1时,易感者、潜伏者、活跃者和退出者趋势变化如图6所示。
当α'=0.25时,在平台上有1/4的舆情信息正在传播,在31h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达499 140人,舆情在82h后基本消退;当α'=0.5时,在平台上有1/2的舆情信息正在传播,在23h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达609 023人,舆情在75h后基本消退;当α'=0.75时,在平台上有3/4的舆情信息正在传播,在20h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达661 328人,舆情在70h后基本消退;当α'=1时,在平台上有1/4的舆情信息正在传播,在18h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达 692 812 人,舆情在65h后基本消退。
由此可知:活跃率越高,给定时间段内传播状态的信息数量占整个信息网络的比例越大,舆情峰值到来时间越短,峰值时活跃者人数越多,舆情消退越快。所以当发生重大事故网络舆情时,短时间内提升传播状态的信息数量比例,会让网络舆情较快消退。
退出率表示在一定时间内不再受到舆情信息影响的人数与总人数的比值。这个值可以用来衡量舆情的持续影响力和信息的传播效果。
若设置总人数N=1 000 000,传染率β=2,活跃率α'=0.75,退出率γ'分别取0.05、0.1、0.2、0.4时,易感者、潜伏者、活跃者和退出者趋势变化如图7所示。
γ'=0.05时,每天有感染者群体的1/20从感染状态恢复,在20h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达785 371人,舆情在110h后消退;当γ'=0.1时,每天有感染者群体的1/10从感染状态恢复,在20h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达 661 328 人,舆情在70h后消退;当γ'=0.2时,每天有感染者群体的1/5从感染状态恢复,在20h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达 493 453 人,舆情在48h后消退;当γ'=0.4时,每天有感染者群体的2/5从感染状态恢复,在23h左右达到舆情峰值,峰值时具备舆情传染性的活跃者人数达 296 346 人,舆情在38h后消退。
由此可知:退出率变化对舆情峰值到来时间影响不大,退出率越高,舆情峰值时活跃者人数越少,舆情消退越快。所以,当发生重大事故网络舆情时,及时发布事实信息,引导正确舆论方向,可在较短时间内使网络舆情消退。
深入开展传染率、活跃率及退出率等影响因素的分析,对于网络舆情的传播过程及预防预控研究的开展十分重要。网络舆情预防预控的价值在于及早识别、理解和应对潜在的舆情风险。通过建立舆情走向预测模型,预测未来舆情事件的发展趋势、关键节点和可能的影响,提供更有针对性的舆情管理和决策支持。
1) 提出基于主动安全理念的事故灾害网络舆情分析方法,该方法依次结合情感分析模型、主题计算模型及SEIR模型等多种方法,展现出较好的事故灾害网络舆情分析性能。文中提出的CDBN-TCN-CRF情感分析模型及TWAE主题模型,展现出更好的情感分析及主题分类性能。同时,通过对传染率、活跃率及退出率等关键参数的分析与研究,展现出SEIR模型对网络舆情走势良好的预测能力。
2) 文中的研究还存在一些局限性:① CDBN-TCN-CRF模型对于不同的任务需要重新训练和调整模型,因此其适应性有限。② TWAE模型需要较长的时间来进行模型训练,模型的训练时间与数据量、模型规模等因素强相关。③ SEIR模型假设人群是均匀的,而在事故灾害的情况下,受灾范围和程度可能会对人群的分布产生重大影响,使得模型预测结果不够准确。在后续的研究工作中,将继续深入开展网络舆情分析模型鲁棒性的研究,设计表现更加优异的网络舆情分析混合模型,推动事故灾害网络舆情分析方法范式的转换。
参考文献 引证文献
排序方式:
[1]
WANG Cong, WANG Zhenpo, ZHANG Zhiqiang, et al. Integrated post-impact planning and active safety control for autonomous vehicles[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(3): 2062-2076.
[2]
ALDIANSYAH M R, SASONGKO P S. Twitter sentiment analysis about public opinion on 4G smartfren network services using convolutional neural network[C]. 3rd International Conference on Informatics and Computational Sciences, 2019: 1-6.
[3]
刘定一, 沈阳阳, 詹天明, 等. 融合微博热点分析和LSTM模型的网络舆情预测方法[J]. 江苏大学学报, 2021, 42(5): 546-553.
LIU Dingyi, SHEN Yangyang, ZHAN Tianming, et al. Network public opinion forecasting method fusing microblog hotspot analysis and LSTM model[J]. Journal of Jiangsu University, 2021, 42(5): 546-553.
[4]
YAN Chun, LIU Jiahui, LIU Wei, et al. Research on public opinion sentiment classification based on attention parallel dual-channel deep learning hybrid model[J]. Engineering Applications of Artificial Intelligence, 2022,116:DOI:10.1016/j.engappai.2022.105448.
[5]
ZHANG Linghan. Design of early warning mechanism of network public opinion using deep learning[C]. 2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering, 2022: 250-252.
[6]
ZHANG Baosheng, HUANG He. Research on evolution and control of network public opinion based on SEIR model with martial law mechanism[C]. 2020 International Conference on Information Science and Education, 2020: 272-276.
[7]
JIANG Changbin, ZHANG Yaoyuan, WANG Hu, et al. Study on coupled social network public opinion communication based on improved SEIR[C]. 2020 IEEE International Conference on Big Data and Cloud Computing, 2020: 1495-1500.
[8]
RAFFAELE D, PATRICIA D, GIUSEPPE G, et al. A modified SEIR model: stiffness analysis and application to the diffusion of fake news[C]. International Conference on Computational Science and Its Applications, 2022: 90-103.
[9]
GENG Lixiao, YANG Shuran, WANG Ke, et al. Modeling public opinion dissemination in a multilayer network with SEIR model based on real social networks[J]. Engineering Applications of Artificial Intelligence, 2023,125:DOI:10.1016/j.engappai.2023.106719.
[10]
LEE H, GROSSE R, RANGANATH R, et al. Unsupervised learning of hierarchical representations with convolutional deep belief networks[J]. Communications of the ACM, 2011, 54(10): 95-103.
[11]
LEA C, VIDAL R, REITER A, et al. Temporal convolutional networks: a unified approach to action segmentation[C]. European Conference on Computer Vision, 2016: 47-54.
[12]
TOLSTIKHIN I, BOUSQUET O, GELLY S, et al. Wasserstein auto-encoders[C]. 6th International Conference on Learning Representations(ICLR 2018), 2018: 1-16.
[13]
方匡南, 任蕊, 朱建平, 等. 基于动态SEIR模型的传染性疾病预测和政策评估[J]. 管理科学学报, 2022, 25(10): 114-126.
FANG Kuangnan, REN Rui, ZHU Jianping, et al. Prediction and policy assessment of infectious diseases transmission using dynamic SEIR model[J]. Journal of Management Sciences in China, 2022, 25(10): 114-126.
[14]
刘丽华. 自然灾害微博舆情的社会计算模型建构研究[D]. 武汉: 武汉大学, 2018.
LIU Lihua. Research on social computing model construction of natural disasters weibo public opinion based on sentiment analysis and topic modeling[D]. Wuhan: Wuhan University, 2018.
[15]
竺佳芳. 顾及时空主题特征的分布式灾害舆情信息获取与分析方法研究[D]. 杭州: 浙江大学, 2019.
ZHU Jiafang. Distributed acquisition and analysis methods of disaster-related public opinions based on spatiotemporal and theme features[D]. Zhejiang: Zhejiang University, 2019.
2024年第34卷第1期
PDF下载
465
204
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.01.0741
  • 接收时间:2023-08-16
  • 首发时间:2025-07-09
  • 出版时间:2024-01-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-08-16
  • 修回日期:2023-11-25
基金
作者信息
    武汉理工大学 管理学院,湖北 武汉 430070

通讯作者:

**谢科范(1963—),男,湖南益阳人,博士,二级教授,主要从事安全科学理论、安全生产管理、安全系统和风险管理等方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.01.0741
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏