[目的/意义] 探索微博舆情传播周期中不同传播者关注的舆情热点和传播内容的主要观点，进而发现舆情传播的特点和规律，为舆情分析与决策提供依据。[方法/过程] 以特定舆情事件的事实文本数据为来源，以生命周期理论和LDA方法为指导，设计研究流程与构建研究模型，对微博舆情事件中不同传播者的话题进行主题研究，其中包括主题抽取和结果语义标注、各阶段的不同传播者主题的语义分析、基于时间维度的舆情主题观点识别与刻画。[结果/结论] 研究发现，论文所提出的研究模型能够挖掘出舆情传播周期中不同传播者的主题结构、观点脉络以及特征，研判出分布在文字当中有关联性的、代表性的、重要的词语。同时，结论中还发现微博中的官媒、大众媒体发布信息中的话题和用户谈论的热点话题具有明显的差异性。
[Purpose/significance] This paper aims to explore the hot spot of public opinion and the main point view of the communication of different communicators in the transmission cycle of micro-blog public opinion and to discover the characteristics and laws of public opinion transmission, which can provide the basis for public opinion analysis and decision making.[Method/process] This study is based on the text data of a true public opinion event. It adopted life cycle theory and LDA method to design research process and construct research model, and researched topics of different communicators in micro-blog public opinion events, including topic extraction and semantic annotation, semantic analysis of different communicators at various stages, recognition and characterization of theme views of public opinion based on time dimension.[Result/conclusion] It is found that the research model proposed in this paper can excavate topic theme structure, view and characteristics of different communicators in the communication cycle of public opinion. And the words with actual meaning and irritating function are related, representative and important. At the same time, the conclusion also found a hot topic in the mass media or the official micro-blog is totally different from micro-blog users.
[1] 陈晓美,高铖,关心惠.网络舆情观点提取的LDA主题模型方法[J].图书情报工作,2015,59(21):21-26.
[2] 张寿华,刘振鹏.网络舆情热点话题聚类方法研究[J].小型微型计算机系统,2013,34(3):471-474.
[3] 李磊,刘继,张竑魁.基于共现分析的网络舆情话题发现及态势演化研究[J].情报科学,2016,34(1):44-47,57.
[4] 钱爱兵.基于主题的网络舆情分析模型及其实现[J].现代图书情报技术,2008(4):49-55.
[5] 梁晓贺,田儒雅,吴蕾,等.基于超网络的微博舆情主题挖掘方法[J].情报理论与实践,2017,40(10):100-105.
[6] LI N, WU D D. Using text mining and sentiment analysis for online forums hotspot detection and forecast[J]. Decision support systems, 2010, 48(2):354-368.
[7] SU L Y F, CACCIATORE M A, LIANG X, et al. Analyzing public sentiments online:combining human-and computer-based content analysis[J]. Information, communication & society, 2017, 20(3):406-427.
[8] 丁晟春,龚思兰,周文杰,等.基于知识库和主题爬虫的南海舆情实时监测研究[J].情报杂志,2016,35(5):32-37.
[9] 张瑜,李兵,刘晨玥.面向主题的微博热门话题舆情监测研究——以"北京单双号限行常态化"舆情分析为例[J].中文信息学报,2015,29(5):143-151,159.
[10] 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.
[11] ZHAO J, DONG L, WU J, et al. Moodlens:an emoticon-based sentiment analysis system for chinese tweets[C]//Proceedings of the 18th ACM SIGKDD international conference on knowledge discovery and data mining. New York:ACM, 2012:1528-1531.
[12] MEI Q, LING X, WONDRA M, et al. Topic sentiment mixture:modeling facets and opinions in weblogs[C]//Proceedings of the 16th international conference on World Wide Web. New York:ACM,2007:171-180.
[13] 关鹏,王曰芬.学科领域生命周期中作者研究兴趣演化分析[J].图书情报工作,2016,60(19):116-124.
[14] 唐晓波,向坤.基于LDA模型和微博热度的热点挖掘[J].图书情报工作, 2014, 58(5):58-63.
[15] 林萍,黄卫东.基于LDA模型的网络舆情事件话题演化分析[J].情报杂志,2013,32(12):26-30.
[16] ZHAO W X, JIANG J, WENG J, et al. Comparing twitter and traditional media using topic models[C]//European conference on information retrieval. Berlin,Heidelberg:Springer-Verlag,2011:338-349.
[17] PENNACCHIOTTI M, GURUMURTHY S. Investigating topic models for social media user recommendation[C]//Proceedings of the 20th international conference companion on World wide web. New York:ACM, 2011:101-102.
[18] 安璐,杜廷尧,余传明,等.突发公共卫生事件的微博主题演化模式和时序趋势——以Twitter和Weibo的埃博拉微博为例[J].情报资料工作, 2016(5):44-52.
[19] 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,2015,33(11):74-78.
[20] 张思龙.微博热点话题预判技术研究[D].郑州:解放军信息工程大学,2013.
[21] MEI Q, LIU C, SU H, et al. A probabilistic approach to spatiotemporal theme pattern mining on weblogs[C]//Proceedings of the 15th international conference on World Wide Web. New York:ACM, 2006:533-542.
[22] 关鹏,王曰芬.基于LDA主题模型和生命周期理论的科学文献主题挖掘[J].情报学报,2015,34(3):286-299.
