基于扎根理论与词典构建的微博突发事件情感分析与舆情引导策略
|
摘要
[目的/意义]网民情感变化是影响政府舆情应对进程、政策、策略的关键。因此,构建科学高效的情感词典,对网民情感分析研究及应对策略的选择具有重要的实际意义。[方法/过程]结合扎根理论的质性研究特点,在情感词典的构造中融入突发事件演化规律影响因素,采用点互信息算法,TF-IDF,统计量等方法对微博表情符号词典及突发事件专属情感词典进行构建,编制了突发事件情感词典,随后选取"6. 22"杭州保姆纵火案微博语料进行情感分析。[结论/结果]实验发现,与不加入影响因素的情感词典相比,本文构造的词典在准确率召回率等指标的对比中均得到了一定程度的提高。同时,结合扎根理论与主题分析的结果,对舆情发展的不同阶段所选择的舆情应对策略提供了参考。
[Purpose/Significance] The emotional change of netizens is the key to the policy of public opinion. Therefore building a scientific and efficient sentiment lexicon will have great practical significance to the analysis of Internet users and the choice of coping strategies. [Method/Process] Combining the qualitative research characteristics of grounded theory,this paper took the factors influencing the evolution of emergencies into consideration in the construction of sentiment dictionaries. The point mutual information algorithm,TF-IDF,statistics and other methods were used to construct the micro-blog Emotions dictionary and the special sentiment lexicon of emergency,thus this paper compiled the Emotion Dictionary of the emergency. Then the "6. 22 Hangzhou nanny arson case" was selected for emotional analysis. [Result/Conclusion] It was found that the sentiment lexicon constructed in this paper had a certain degree of improvement in comparison with the index of accuracy and recall than the previous dictionary. At the same time,combined with the results of root theory and topic extraction analysis,the lexicon would provide reference for the coping strategies chosen in different stages of public opinion development.
[Purpose/Significance] The emotional change of netizens is the key to the policy of public opinion. Therefore building a scientific and efficient sentiment lexicon will have great practical significance to the analysis of Internet users and the choice of coping strategies. [Method/Process] Combining the qualitative research characteristics of grounded theory,this paper took the factors influencing the evolution of emergencies into consideration in the construction of sentiment dictionaries. The point mutual information algorithm,TF-IDF,statistics and other methods were used to construct the micro-blog Emotions dictionary and the special sentiment lexicon of emergency,thus this paper compiled the Emotion Dictionary of the emergency. Then the "6. 22 Hangzhou nanny arson case" was selected for emotional analysis. [Result/Conclusion] It was found that the sentiment lexicon constructed in this paper had a certain degree of improvement in comparison with the index of accuracy and recall than the previous dictionary. At the same time,combined with the results of root theory and topic extraction analysis,the lexicon would provide reference for the coping strategies chosen in different stages of public opinion development.
引文
[1]中国互联网络信息中心.第42次《中国互联网络发展状况统计报告》[EB]. http://www. cnnic. net. cn/hlwfzyj/hlwxzbg/hl-wtjbg/201808/t20180820_70488.htm.
[2]张鹏,兰月新,李昊青,等.基于认知过程的网络谣言综合分类方法研究[J].图书与情报,2016,(4):8-15.
[3]徐蕾,李庆,肖相泽.基于扎根理论的大数据政策共词网络研究[J].现代情报,2018,38(6):157-164.
[4]于兆吉,张嘉桐.基于扎根理论的突发性网络舆情演化影响因素研究[J].东北大学学报:社会科学版,2016,(5):498-502.
[5]黄远,沈乾,刘怡君.微博舆论场:突发事件舆情演化分析的新视角[J].系统工程理论与实践,2015,35(10):2564-2572.
[6]田梅.网络浏览中偶遇信息共享行为影响因素扎根分析[J].图书与情报,2015,(5):117-122.
[7]刘波维,曾润喜.网络舆情研究视角分析[J].情报杂志,2017,(2):91-96.
[8]陈福集,黄江玲.三方博弈视角下的网络舆情演化研究[J].情报科学,2015,33(9):22-26.
[9] Burkholder B T,Toole M J. Evolution of Complex Disasters[J].The Lancet,1995,346(8981):1012-1015.
[10] Coombs W. T. Ongoing Crisis Communication-Planning,Manag-ing and Responding[M]. London:SAGE Publication. INC,1999.
[11]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.
[12]崔鹏,张巍,何毅,等.突发公共事件网络舆情演化及政府应对能力研究[J].现代情报,2018,38(2):75-83,95.
[13]涂海丽,唐晓波.基于在线评论的游客情感分析模型构建[J].现代情报,2016,36(4):70-77.
[14]刘甲学,陶易.基于情感分析的评论数据用户满意度影响因素研究[J].现代情报,2017,37(7):66-69.
[15]崔彦琛,张鹏,兰月新,等.消防突发事件网络舆情情感词典构建研究[J].情报杂志. 2018,37(10):154-160.
[16]夏一雪,兰月新,曾润喜,等.全媒体语境下突发事件舆情信息风险管理模式研究[J].图书与情报,2016,(3):11-18.
[17]曾润喜,徐晓林.网络舆情的传播规律与网民行为:一个实证研究[J].中国行政管理,2010,305(11):16-20.
[18]王琦,王琳.在线评论情感倾向的影响效应及管理措施[J].北京邮电大学学报:社会科学版,2015,17(1):43-51.
[19]李纲,王晓,叶光辉.国内突发事件预警研究评述[J].情报理论与实践,2017,40(7):138-144.
[20]兰月新.面向舆情大数据的群体性事件预警研究[M].天津:天津大学出版社,2018.
[21]刘兵.情感分析:挖掘观点、情感和情绪[M].北京:机械工业出版社,2017.
[22]李婷婷,姬东鸿.基于SVM和CRF多特征组合的微博情感分析[J].计算机应用研究,2015,32(4):978-981.
[23] Noelle-Neumann,E. Zhe Spiral of Silence:Public Opinion-OurSocial Skin(Second edition)[M]. Chicago:the university of Chi-cago Press,1993:59.
[24] Zhou Y,Moy P. Parsing Framing Processes:The Interplay Be-tween Online Public Opinion and Media Coverage[J]. Journal ofCommunication,2007,57(1):79-98.
[25] Turney P D,Littman M L. Unsupervised Learning of Semantic O-rientation from a Hundred-Billion-Word Corpus[R]. National Re-search Council of Canada,Tech. Rep:EGB 1094,2002.
[26]赵晓航.基于情感分析与主题分析的“后微博”时代突发事件政府信息公开研究———以新浪微博“天津爆炸”话题为例[J].图书情报工作,2016,60(20):104-111.
[2]张鹏,兰月新,李昊青,等.基于认知过程的网络谣言综合分类方法研究[J].图书与情报,2016,(4):8-15.
[3]徐蕾,李庆,肖相泽.基于扎根理论的大数据政策共词网络研究[J].现代情报,2018,38(6):157-164.
[4]于兆吉,张嘉桐.基于扎根理论的突发性网络舆情演化影响因素研究[J].东北大学学报:社会科学版,2016,(5):498-502.
[5]黄远,沈乾,刘怡君.微博舆论场:突发事件舆情演化分析的新视角[J].系统工程理论与实践,2015,35(10):2564-2572.
[6]田梅.网络浏览中偶遇信息共享行为影响因素扎根分析[J].图书与情报,2015,(5):117-122.
[7]刘波维,曾润喜.网络舆情研究视角分析[J].情报杂志,2017,(2):91-96.
[8]陈福集,黄江玲.三方博弈视角下的网络舆情演化研究[J].情报科学,2015,33(9):22-26.
[9] Burkholder B T,Toole M J. Evolution of Complex Disasters[J].The Lancet,1995,346(8981):1012-1015.
[10] Coombs W. T. Ongoing Crisis Communication-Planning,Manag-ing and Responding[M]. London:SAGE Publication. INC,1999.
[11]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.
[12]崔鹏,张巍,何毅,等.突发公共事件网络舆情演化及政府应对能力研究[J].现代情报,2018,38(2):75-83,95.
[13]涂海丽,唐晓波.基于在线评论的游客情感分析模型构建[J].现代情报,2016,36(4):70-77.
[14]刘甲学,陶易.基于情感分析的评论数据用户满意度影响因素研究[J].现代情报,2017,37(7):66-69.
[15]崔彦琛,张鹏,兰月新,等.消防突发事件网络舆情情感词典构建研究[J].情报杂志. 2018,37(10):154-160.
[16]夏一雪,兰月新,曾润喜,等.全媒体语境下突发事件舆情信息风险管理模式研究[J].图书与情报,2016,(3):11-18.
[17]曾润喜,徐晓林.网络舆情的传播规律与网民行为:一个实证研究[J].中国行政管理,2010,305(11):16-20.
[18]王琦,王琳.在线评论情感倾向的影响效应及管理措施[J].北京邮电大学学报:社会科学版,2015,17(1):43-51.
[19]李纲,王晓,叶光辉.国内突发事件预警研究评述[J].情报理论与实践,2017,40(7):138-144.
[20]兰月新.面向舆情大数据的群体性事件预警研究[M].天津:天津大学出版社,2018.
[21]刘兵.情感分析:挖掘观点、情感和情绪[M].北京:机械工业出版社,2017.
[22]李婷婷,姬东鸿.基于SVM和CRF多特征组合的微博情感分析[J].计算机应用研究,2015,32(4):978-981.
[23] Noelle-Neumann,E. Zhe Spiral of Silence:Public Opinion-OurSocial Skin(Second edition)[M]. Chicago:the university of Chi-cago Press,1993:59.
[24] Zhou Y,Moy P. Parsing Framing Processes:The Interplay Be-tween Online Public Opinion and Media Coverage[J]. Journal ofCommunication,2007,57(1):79-98.
[25] Turney P D,Littman M L. Unsupervised Learning of Semantic O-rientation from a Hundred-Billion-Word Corpus[R]. National Re-search Council of Canada,Tech. Rep:EGB 1094,2002.
[26]赵晓航.基于情感分析与主题分析的“后微博”时代突发事件政府信息公开研究———以新浪微博“天津爆炸”话题为例[J].图书情报工作,2016,60(20):104-111.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |