JIANG Wen-ting,LIN Shao-rui,LIAO Ying-qian.SAS:a System Via Situation Awareness on EndogenousBig Data for Smart Grid Security[J].Journal of Chengdu University of Information Technology,2018,(03):290-295.[doi:10.16836/j.cnki.jcuit.2018.03.012]
SAS:用于智能电网安全的移动内生大数据态势感知系统
- Title:
- SAS:a System Via Situation Awareness on EndogenousBig Data for Smart Grid Security
- 文章编号:
- 2096-1618(2018)03-0290-06
- 分类号:
- TP393.08
- 文献标志码:
- A
- 摘要:
- 智能电网安全管理需要对用户行为进行感知和分析,通过对移动端用户的态势进行感知,从而了解智能电网部署的服务质量。实现移动端用户的态势感知需要对移动端内生大数据进行深入的分析,然而目前相关分析还不多见。构造了一种新的文本情感值计算方法,以一款常用APP为例分析了获取的11万条特定事件的新闻评论情感值,并对此进行统计分析。结果显示,在情感缓和的时间段发生新闻热点时对新闻的评论的情感值波动变化会急剧增加,情感值方差会急剧上升。而当新的新闻发生在另一新闻热点影响时间段内则评论的情感值波动变化趋于平稳乃至呈下降。这些结果对智能电网用户感知具有重要的应用价值,同时也可以用于舆情监控与预警、网络监管与建模。
- Abstract:
- In the security management of Smart grid, user behaviors should be sensed and analyzed, which is always achieved by situation awareness on client and helps for improving QoS. To achieve the situational awareness of mobile end users, it is necessary to carry out in-depth analysis on the endogenous big data of mobile terminal,at present, however, relevant analysis is rare.In this paper, a new method for calculating the emotional value of text is constructed, and a common APP is used as an example to analyze the emotional value of the news commentary on the 110000 specific events obtained, and the statistical analysis is carried out.The results show that the emotional value fluctuation of the news will increase sharply when the news hot spot occurs during the period of emotional relaxation, and the variance of emotional value will increase sharply. However, when the new news happened in another news hot spot, the emotional value fluctuation of the comments tended to be stable and even declined. These system and research results provide valuable information for networking situation awareness on popular opinions and network event supervision or modeling.
参考文献/References:
[1] 赵妍妍,秦兵,刘挺.文本情感分析[J].软件学报,2010,21(8):1834-1848.
[2] 杨经,林世平.基于SVM的文本词句情感分析[J].计算机应用与软件,2011,28(9):225-228.
[3] 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.
[4] 石慧,贾代平,苗培.基于词频信息的改进信息增益文本特征选择算法[J].计算机应用,2014,34(11):3279-3282.
[5] Wu Ho Chung,Luk, Robert Wing Pong,Wong,Kam Fai,et al.Interpreting TF-IDF term weights as making relevance decisions[J].ACM Transactions on Information Systems,2008,26(3):1-37.
[6] 熊德兰,程菊明,田胜利.基于HowNet的句子褒贬倾向性研究[J].计算机工程与应用,2008,44(22):143-145.
[7] 王振宇,吴泽衡,胡方涛.基于HowNet和PMI的词语情感极性计算[J].计算机工程,2012,38(15):187-189.
[8] Dong Z,Dong Q.HowNet-a hybrid language and knowledge resource[C].International Conference on Natural Language Processing and Knowledge Engineering Proceedings,2003.
[9] 杨小平,马奇凤,余力,等.评论簇在网络舆论中的情感倾向代表性研究[J].现代图书情报技术,2016,32(7):51-59.
[10] Xue B,Fu C,Zhan S.A Study on Sentiment Computing and Classification of SinaWeibo with Word2vec[C].IEEE International Congress on Big Data,2014:358-363.
[11] 赵文清,侯小可,沙海虹.语义规则在微博热点话题情感分析中的应用[J].智能系统学报,2014,9(1):121-125.
[12] 王文,王树锋,李洪华.基于文本语义和表情倾向的微博情感分析方法[J].南京理工大学学报(自然科学版),2014,38(6):733-738.
[13] 王雍凯,毛存礼,余正涛,等.基于图的新闻事件主题句抽取方法[J].南京理工大学学报(自然科学版),2016,40(4):438-443.
[14] 陈忆金,曹树金,陈桂鸿.网络舆情意见挖掘:用户评论情感倾向分析研究[J].图书情报知识,2013(6):90-96.
[15] 周胜臣,瞿文婷,石英子,等.中文微博情感分析研究综述[J].计算机应用与软件,2013,30(3):161-164.
备注/Memo
收稿日期:2018-03-30基金项目:国家重点研发计划资助项目(2016YFB0901200); 广东电网科技资助项目(036000KK52170002)