面向突发事件应急管理的情感词典构建——以“暴雨洪涝”灾害为例
|
摘要
在复杂的网络舆论生态中,突发事件中的舆情发展更具多变性和难以预测性,通用情感词典已难以适应当前突发事件文本情感分析的需要,建立面向突发事件应急管理的专业情感词典,对于提升网民情感分析的准确度和及时把握舆情走向具有重要意义。据此,采用机器采集加人工构建的方式,以近5年的10起暴雨洪涝灾害的微博评论文本为语料,建立"突发事件·暴雨洪涝"情感词典。经检验发现,该词典显著提高了暴雨洪涝文本情感分析的正确率和召回率,为突发事件的应急管理提供了更为精确和可操作的决策基础。
In the complex network public-opinion ecology,the development of public opinion in emergencies is more and more changeable and unpredictable.The general sentiment lexicon has a great difficulty to adapt to the current emotional analysis in unexpected events.It is of great significance to establish an emergency sentiment lexicon,because it can improve the accuracy of sentiment analysis and forecast the public opinion timely.In this paper,we use the method of machine acquisition and artificial construction to establish the "emergency:rainstorm and flood" sentiment lexicon,with 10 rainstorm and flood disasters' microblogging commentary in recent 5 years.It has been found that the emergency sentiment lexicon has significantly improved the correct rate and recall rate of the emotional analysis of the rainstorm and flooding disasters' microblogging commentary,and provided a more accurate and operational basis for the emergency management.
In the complex network public-opinion ecology,the development of public opinion in emergencies is more and more changeable and unpredictable.The general sentiment lexicon has a great difficulty to adapt to the current emotional analysis in unexpected events.It is of great significance to establish an emergency sentiment lexicon,because it can improve the accuracy of sentiment analysis and forecast the public opinion timely.In this paper,we use the method of machine acquisition and artificial construction to establish the "emergency:rainstorm and flood" sentiment lexicon,with 10 rainstorm and flood disasters' microblogging commentary in recent 5 years.It has been found that the emergency sentiment lexicon has significantly improved the correct rate and recall rate of the emotional analysis of the rainstorm and flooding disasters' microblogging commentary,and provided a more accurate and operational basis for the emergency management.
引文
[1] 王科,夏睿.情感词典自动构建方法综述[J].自动化学报,2016,42(4):495-511.
[2] 赵妍妍,秦兵,刘挺.文本情感分析[J].软件学报,2010,21(8):1834-1848.
[3] BingLiu.Sentiment Analysis and Opinion Mining[M].Williston:Morgan&Claypool Publishers,2012:4.
[4] 刘志明,刘鲁.基于机器学习的中文微博情感分类实证研究[J].计算机工程与应用,2012,48(1):1-4.
[5] 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.
[6] 刘强.文本的特征提取及KNN分类优化问题研究[D].广州:华南理工大学,2009:1.
[7] 马龙,宫玉龙.文本情感分析研究综述[J].电子科技,2014,27(11):180-184.
[8] 杨超,冯时,王大玲,等.基于情感词典拓展技术的网络舆情倾向性分析[J].小型微型计算机系统,2010,31(4):691-695.
[9] Xu Ge,Meng Xinfan,Wang Houfeng.Build Chinese emotion lexicons using a graph-based algorithm and multiple resources[C]//Proceedings of the 23rd International Conference on Computational Linguistics(COLING 10).Strouds-burg,PA,USA:Association for Computational Linguistics,2010:1209-1217.
[10] 阳爱民,林江豪,周咏梅.中文文本情感词典构建方法[J].计算机科学与探索,2013,7(11):1033-1039.
[11] 肖红,许少华.基于句法分析和情感词典的网络舆情倾向性分析研究[J],小型微型计算机系统,2014,35(4):811-813.
[12] 唐超.网络情绪演进的实证研究[J].情报杂志,2012,31(10):48-52.
[13] 黄金兰,林以正,谢亦泰等.中文版“语文探索与字词计算”词典之建立[J].中华心理学刊,2012,54(2):185-201.
[14] 乐国安,董颖红.情绪的基本结构:争论、应用及其前瞻[J].南开学报:哲学社会科学版,2013(1):140-150.
[15] Waston D,Clark LA.“Measurement and Mismeasurement of Mood:Recurrent and Emergent Issues”.Journal of Personality Assessment,1997,68(2):267.
[16] Ekman P,Friesen WV.“Constants across Cultures in the Face and Emotion”,Journal of Personality and Social Psychology.1971,17(2):124.
[2] 赵妍妍,秦兵,刘挺.文本情感分析[J].软件学报,2010,21(8):1834-1848.
[3] BingLiu.Sentiment Analysis and Opinion Mining[M].Williston:Morgan&Claypool Publishers,2012:4.
[4] 刘志明,刘鲁.基于机器学习的中文微博情感分类实证研究[J].计算机工程与应用,2012,48(1):1-4.
[5] 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.
[6] 刘强.文本的特征提取及KNN分类优化问题研究[D].广州:华南理工大学,2009:1.
[7] 马龙,宫玉龙.文本情感分析研究综述[J].电子科技,2014,27(11):180-184.
[8] 杨超,冯时,王大玲,等.基于情感词典拓展技术的网络舆情倾向性分析[J].小型微型计算机系统,2010,31(4):691-695.
[9] Xu Ge,Meng Xinfan,Wang Houfeng.Build Chinese emotion lexicons using a graph-based algorithm and multiple resources[C]//Proceedings of the 23rd International Conference on Computational Linguistics(COLING 10).Strouds-burg,PA,USA:Association for Computational Linguistics,2010:1209-1217.
[10] 阳爱民,林江豪,周咏梅.中文文本情感词典构建方法[J].计算机科学与探索,2013,7(11):1033-1039.
[11] 肖红,许少华.基于句法分析和情感词典的网络舆情倾向性分析研究[J],小型微型计算机系统,2014,35(4):811-813.
[12] 唐超.网络情绪演进的实证研究[J].情报杂志,2012,31(10):48-52.
[13] 黄金兰,林以正,谢亦泰等.中文版“语文探索与字词计算”词典之建立[J].中华心理学刊,2012,54(2):185-201.
[14] 乐国安,董颖红.情绪的基本结构:争论、应用及其前瞻[J].南开学报:哲学社会科学版,2013(1):140-150.
[15] Waston D,Clark LA.“Measurement and Mismeasurement of Mood:Recurrent and Emergent Issues”.Journal of Personality Assessment,1997,68(2):267.
[16] Ekman P,Friesen WV.“Constants across Cultures in the Face and Emotion”,Journal of Personality and Social Psychology.1971,17(2):124.