[Purpose/significance] Based on social media, this paper explores the dynamic classification of different stakeholders in the information life cycle of emergencies and the evolution rules of their concerns, so as to provide basis for more accurate crisis information monitoring and dynamic decision-making.[Method/process] Based on the factual text data of specific crisis events, guided by stakeholder theory and dynamic topic model, a three-dimensional dynamic topic evolution model was constructed to mine the classification and topic concerns of different stakeholders in social media crisis events. It included time granularity division, quantitative evaluation of stakeholders, identification and characterization of crisis themes based on time and subject. Finally, the dynamic trend was characterized by visualization tools.[Result/conclusion] Based on the three-dimensional dynamic theme evolution model, the composition and classification of stakeholders have obvious differences in different stages. At the same time, their focus themes and behavior characteristics also show different preferences and dynamic differences. The dynamics of the crisis stakeholders and the crisis theme are effectively combined, which can more comprehensively express the characteristics and regulars of public opinion dissemination.
[1] NAWEED A, BYE R. Joint cognitive systems:patterns in cognitive systems engineering[J]. Ergonomics, 2008, 51(5):768-770.
[2] 马晓悦,薛鹏珍.大数据环境下的信息时空分析与应用研究评述[J].情报理论与实践, 2020, 43(2):164-170.
[3] 丁学君, 樊荣, 苗蕊,等. 社会化媒体中突发公共卫生事件舆情传播规律研究[J]. 信息系统学报, 2018(2):1-14.
[4] 刘雅姝,张海涛,徐海玲,等.多维特征融合的网络舆情突发事件演化话题图谱研究[J].情报学报,2019,38(8):798-806.
[5] ZAHRA K, IMRAN M, OSTERMANN F O. Automatic identification of eyewitness messages on Twitter during disasters[EB/OL].[2021-01-27]. https://www.sciencedirect.com/science/article/pii/S0306457319303590.
[6] 马哲坤,涂艳.基于知识图谱的网络舆情突发话题内容监测研究[J].情报科学, 2019, 37(2):33-39.
[7] 安璐,吴林.融合主题与情感特征的突发事件微博舆情演化分析[J].图书情报工作, 2017, 61(15):120-129.
[8] TOWERS S, AFZAL S, BERNAL G, et al. Mass media and the contagion of fear:the case of Ebola in America[EB/OL].[2021-01-27]. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0129179.
[9] STARBIRD K, PALEN L. "Voluntweeters":self-organizing by digital volunteers in times of crisis[C]//Proceedings of the SIGCHI conference on human factors in computing systems. Vancouver:ACM Press,2011:1071-1080.
[10] YUN H. Analysis of similarity of twitter topic categories among regions[J]. Journal of information and communication convergence engineering, 2012, 10(1):27-32.
[11] LUDWIG T, KOTTHAUS C, REUTER C, et al. Situated crowdsourcing during disasters:Managing the tasks of spontaneous volunteers through public displays[J]. International journal of human-computer studies, 2017, 102:103-121.
[12] 邓三鸿,刘喜文,蒋勋.基于利益相关者理论的突发事件案例知识库构建研究[J].图书与情报, 2015(3):1-8.
[13] MALTONI C, ROSSI C, SÁNCHEZ G. Improving resilience to emergencies through advanced cyber technologies:the I-REACT project[J]. GEOmedia, 2017, 21(3):18-22.
[14] 沙勇忠,刘红芹.公共危机的利益相关者分析模型[J].科学经济社会, 2009, 27(1):58-61.
[15] APOSTOLAKIS G E, PICKETT S E. Deliberation:integrating analytical results in to environmental decisions involving multiple stakeholders[J].Risk analysis,1998,18(5):621-634.
[16] VARI A, LINNEROOTH-BAYER J, FERENCZ Z. Stakeholder views on flood risk management in hungary's Upper Tisza Basin[J]. Risk analysis, 2003, 23(3):585-600.
[17] WILSON T D. On user studies and information needs[J].Journal of documentation,1981,37(1):3-15.
[18] SJÖBERG L.Attitudesand risk perceptions of stakeholders in a nuclear waste siting issue[J]. Risk analysis, 2003, 23(4):739-749.
[19] MAASSEN P. The changing roles of stakeholders in Dutch university governance[J]. European journal of education, 2000, 35(4):449-464.
[20] KLENK J S. Emergency information management and telecommunications[J]. Journal of dairy research, 1997, 46(2):1045-1057.
[21] REGO A J. National disaster management information systems & networks:an Asian overview[EB/OL].[2021-01-27]. http://adpc.net/infores/adpc-documents/paperatgdin01.pdf.
[22] WU G X. Information needs and flow for disaster management[EB/OL].[2021-01-27].https://www.itu.int/en/ITU-D/Emergency-Telecommunications/Documents/Thailand_2006/final1/Session%207/SESSION%207%20[ESCAP]%20Mr%20Wu%20Guoxiang.pdf.
[23] ANDERSSON T. Adaptation to climate change-gendered processes, power and places in the national adaptation programmes of action[EB/OL].[2021-01-27]. http://lup.lub.lu.se/luur/download?func=downloadFile&recordOId=1324113&fileOId=1324114.
[24] KUUSISTO T, KUUSISTO R, YLINIEMI T. Information needs of strategic level decision-makers in crisis situations[C]//Proceedings of the 4th European conference on information warfare and security. Glamorgan:University of Glamorgan,2005:187-194.
[25] GHAFARIAN S H, YAZDI H S. Identifying crisis-related informative tweets using learning on distributions[EB/OL].[2021-01-28]. https://www.sciencedirect.com/science/article/pii/S030645731930322X.
[26] ZHENG L, SHEN C, TANG L, et al. Using data mining techniques to address critical information exchange needs in disaster affected public-private networks[C]//Proceedings of the 16th ACM SIGKDD international conference on knowledge discovery and data mining.Washington, DC:ACM Press, 2010:125-134.
[27] RYAN B. A model to explain information seeking behaviour by individuals in the response phase of a disaster[J]. Library & information science research, 2018, 40(2):73-85.
[28] SAYYADI H, RASCHID L. A graph analytical approach for topic detection[EB/OL].[2021-01-28]. https://dl.acm.org/doi/10.1145/2542214.2542215.
[29] YAN S, TANG S T, PEI S, et al. The spreading of opposite opinions on online social networks with authoritative nodes[J]. Physica a-statistical mechanics & its applications, 2013, 392(17):3846-3855.
[30] WANG Q S, YANG X, XI W Y. Effects of group arguments on rumor belief and transmission in online communities:an information cascade and group polarization perspective[J]. Information & management, 2018, 55(4):441-449.
[31] BLEI D M, LAFFERTY J D. Dynamic topic models[C]//Proceedings of the 23rd international conference on machine learning. New York:ACM Press, 2006:113-120.
[32] SHERCHAN W, PERVIN S, BUTLER C J, et al. Harnessing Twitter and Instagram for disaster management[EB/OL].[2021-01-28]. https://ieeexplore.ieee.org/abstract/document/8167723.
[33] FINK S. Crisis management:planning for the inevitable[M]. New York:American Management Association, 1986.
[34] YANG M C, RIM H C. Identifying interesting Twitter contents using topical analysis[J]. Expert systems with applications, 2014, 41(9):4330-4336.
[35] VOSECKY J, JIANG D, LEUNG K W T, et al. Integrating social and auxiliary semantics for multifaceted topic modeling in Twitter[EB/OL].[2021-01-28]. https://dl.acm.org/doi/10.1145/2651403.
[36] FATHI R, THOM D, KOCH S, et al. VOST:a case study in voluntary digital participation for collaborative emergency management[EB/OL].[2021-01-28]. https://www.sciencedirect.com/science/article/pii/S0306457319302316.
[37] HASAN M, ORGUN M A, SCHWITTER R. Real-time event detection from the Twitter data stream using the TwitterNews+ Framework[J]. Information processing & management, 2019, 56(3):1146-1165.
[38] DAKICHE N, TAYEB F B S, SLIMANI Y, et al. Tracking community evolution in social networks:a survey[J]. Information processing & management, 2019,56(3):1084-1102.
[39] FU C G. Tracking user-role evolution via topic modeling in community question answering[EB/OL].[2021-01-28]. https://www.sciencedirect.com/science/article/pii/S030645731830709X.
[40] 郑昌兴, 苏新宁, 刘喜文. 突发事件网络舆情分析模型构建——基于利益相关者视阈[J]. 情报杂志, 2015,34(4):71-75.
[41] 安璐,杜廷尧,李纲,等.突发公共卫生事件利益相关者在社交媒体中的关注点及演化模式[J].情报学报, 2018, 37(4):394-405.
[42] 曹树金,马翠嫦.信息聚合概念的构成与聚合模式研究[J].中国图书馆学报, 2016, 42(3):4-19.
