[目的/意义]构建突发公共卫生事件利益相关者的社会网络情感网络图谱，以可视化的方式分析突发公共卫生事件中各类利益相关者的情感状态和分布，探寻利益相关者之间的情感传播路径，并结合舆情话题综合分析利益相关者的情感演化态势。[方法/过程]以"魏则西事件"为例，通过微博转发关系构建微博用户的社会关系网络，同时标识各用户的利益相关者类型，并计算用户的情感类型及情感强度嵌入社会网络中构建出社会网络情感图谱。[结果/结论]普通群众的情绪更强烈且易受意见领袖影响，在事件爆发期和蔓延期，主流媒体和自媒体对普通群众的情感影响较大，在衰退期，政府人员和医护人员的参与增加且情感影响变大。随着舆情的演化，各类利益相关者的主导情感也随着变化，自媒体和企业在情感传播中起重要的桥梁作用。
[Purpose/significance] Social networks such as microblogs play an important role in disseminating information and emotions during public health emergencies. This study aims to put forward the design scheme and analysis method of the social network sentiment map of the stakeholders in public health emergencies. The sentiment network map can visualize the emotional state and distribution of stakeholders in public health emergencies. Users can explore and analyze the propagation path and evolution of stakeholders' emotions towards the topics in public opinions.[Method/process] Taking "Wei Zexi incident" as an example, this paper constructed the social network of micro-blog users through the forwarding relationship of micro-blog. Meanwhile,identifying the types of stakeholders and calculating the users' emotion type and emotional intensity which were used to be embedded into the social network to construct the sentiment network map.[Result/conclusion] Firstly, ordinary people are more emotional and easily influenced by opinion leaders.In the outbreak and the spreading period of the event, the mainstream media and we-media have a greater impact on the public emotion.In the recession, the government and healthcare providers play a more important role in emotional influence. Secondly, with the evolution of public opinions, the dominant emotions of various stakeholders have also changed.Thirdly, we-media and enterprises act as bridges in the dissemination of emotions.
[1] MILLER V. New media, networking and phatic culture[J].Convergence:the international journal of research into new media technologies,2008,14(4):387-400.
[2] World Health Organization. Ebola situation report[EB/OL].[2016-03-26].http://apps.who.int/iris/bitstream/10665/192654/1/ebolasitrep_4Nov2015_eng.pdf?ua=1.
[3] 魏韡,向阳,陈千. 中文文本情感分析综述[J]. 计算机应用,2011,31(12):3321-3323.
[4] PANG B, LEE L, VAITHYANATHAN S. Thumbs up?Sentiment classification using machine learning techniques[C]//Proceedings of the 2002 conference on empirical methods in natural language processing. Stroudsburg:Association for Computational Linguistics, 2002:79-86.
[5] LI S, ZONG C, WANG X. Sentiment classification through combining classifiers with multiple feature sets[C]//International Conference on natural language processing and knowledge engineering. New York:IEEE, 2007:135-140.
[6] HU M, LIU B. Mining and summarizing customer reviews[C]//Proceedings of the tenth ACM SIGKDD international conference on knowledge discovery and data mining.New York:ACM,2004:168-177.
[7] LOIA V, SENATORE S. A fuzzy-oriented sentic analysis to capture the human emotion in Web-based content[J]. Knowledge-based systems, 2014, 58(1):75-85.
[8] 冯时,付永陈,阳锋,等. 基于依存句法的博文情感倾向分析研究[J]. 计算机研究与发展,2012,49(11):2395-2406.
[9] WANG D, SUTCLIFFE A, ZENG X J. A trust-based multi-ego social network model to investigate emotion diffusion[J]. Social network analysis and mining, 2011, 1(4):287-299.
[10] 戴杏云, 张柳, 戴伟辉,等. 社交网络的情感图谱研究[J]. 管理评论, 2016, 28(8):79-86.
[11] MITROVIC M, PALTOGLOU G, TADIC B. Networks and emotion-driven user communities at popular blogs[J]. The European physical journal, 2010, 77(4):597-609.
[12] JÉRÔME K, LOMMATZSCH A, BAUCKHAGE C. The Slashdot Zoo:mining a social network with negative edges[C]//Proceedings of the 18th international conference on World Wide Web. New York:ACM, 2009:741-750.
[13] TANG J, ZHANG Y, SUN J, et al. Quantitative study of individual emotional states in social networks[J]. IEEE transactions on affective computing, 2012, 3(2):132-144.
[14] YAN S, TANG S, 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.
[15] ZHANG C, LIU Y, WANG C. Time-space varying visual analysis of micro-blog sentiment[C]//International symposium on visual information communication and interaction. New York:ACM, 2013:64-71.
[16] 杨春勇. 基于新浪微博的舆情挖掘及其三维可视化设计[D]. 合肥:中国科学技术大学, 2013.
[17] 纪雪梅. 特定事件情境下中文微博用户情感挖掘与传播研究[D]. 天津:南开大学, 2014.
[18] 陈福集, 黄江玲. 基于演化博弈的网络舆情热点话题传播模型研究[J]. 情报科学, 2015, 32(11):74-78.
[19] 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, 33(9):123-128.
[20] WU Y, YAO Y, WANG L. A novel emergence model of publicopinion based on small-world network[J]. Journal of keyengineering materials,2011, 474-476:2263-2268.
[21] 董坚峰. 面向公共危机预警的网络舆情分析研究[D]. 武汉:武汉大学信息管理学院,2013.
[22] 张玉亮. 突发公共事件网络舆情的生成原因与导控策略——基于网络舆情主体心理的分析视阈[J]. 情报杂志,2012,31(4):54-57.
[23] CHE W, LI Z, LIU T. LTP:a Chinese language technology platform[J]. Journal of Chinese information processing, 2010, 2(6):13-16.
[24] 徐琳宏,林鸿飞,潘宇,等. 情感词汇本体的构造[J].情报学报, 2008, 27(2):180-185.
[25] 韩忠明,张玉沙,张慧,等.有效的中文微博短文本倾向性分类算法[J]. 计算机应用与软件,2012,29(10):89-93.
[26] 王铁套,王国营,陈越,等. 基于语义模式与词汇情感倾向的舆情态势研究[J]. 计算机工程与设计,2012,33(1):74-77.
[27] 杜振雷. 面向微博短文本的情感分析研究[D].北京:北京信息科技大学,2013.
[28] BASTIAN M, HEYMANN S, JACOMY M. Gephi:an open source software for exploring and manipulating networks[EB/OL].[2017-03-21].https://www.researchgate.net/publication/303214441_Gephi_An_Open_Source_Software_for_Exploring_and_Manipulating_Networks.
[29] 李凯晴. 微博在突发公共卫生事件中的舆论引导作用——以"魏则西"事件为例[J]. 视听,2016,11(9):123-124.
[30] JACOMY M, VENTURINI T, HEYMANN S, et al. ForceAtlas2, a continuous graph layout algorithm for handy network visualization designed for the Gephi software[EB/OL].[2017-03-21].http://dx.doi.org/10.1371/journal.pone.0098679.
[31] FRUCHTERMAN T MJ, REINGOLD EM. Graph drawing by force-directed placement[J]. Software:practice and experience,1991,21(11):1129-1164.
