Please wait a minute...
Advanced Search
数据分析与知识发现  2021, Vol. 5 Issue (11): 59-67     https://doi.org/10.11925/infotech.2096-3467.2021.0525
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于CEEMDAN-BP模型的突发事件网络舆情预测研究*
程铁军1,王曼1,黄宝凤1,冯兰萍2()
1南京邮电大学经济学院 南京 210023
2河海大学商学院 常州 213022
Predicting Online Public Opinion in Emergencies Based on CEEMDAN-BP
Cheng Tiejun1,Wang Man1,Huang Baofeng1,Feng Lanping2()
1School of Economics, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
2Business School, Hohai University, Changzhou 213022, China
全文: PDF (1015 KB)   HTML ( 13
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 研究突发事件网络舆情发展趋势的预测问题。【方法】 综合考虑多重不确定因素对网络舆情演化的影响,本文基于数据分解的研究思路,利用自适应噪声完备集成经验模态分解、BP神经网络以及相空间重构理论构建基于CEEMDAN-BP的舆情预测方法,并结合多起突发事件案例进行实证研究。【结果】 研究结果表明,CEEMDAN-BP模型能够较好地预测突发事件网络舆情的发展趋势,三个案例事件舆情预测的平均绝对误差分别为8.60%、17.98%、11.97%,其模型的预测性能优于CEEMDAN-SVM、EMD-BP、EMD-SVM、BP神经网络模型以及SVM模型。【局限】 实验数据是以天为单位进行统计,未能全面反映出舆情演变的变化趋势。【结论】 基于数据分解构建的CEEMDAN-BP模型能够有效预测突发事件网络舆情的发展趋势,可为相关部门做好突发事件网络舆情的管控和预警提供理论支持。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
程铁军
王曼
黄宝凤
冯兰萍
关键词 突发事件网络舆情CEEMDAN分解相空间重构BP神经网络    
Abstract

[Objective] This paper tries to predict the development trend of online public opinion in emergencies. [Methods] First, we identified multiple uncertain factors affecting the evolution of online public opinion. Then, we constructed a CEEMDAN-BP prediction model combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, phase-space reconstruction and Back Propagation Network. Finally, we conducted an empirical study to examine the new model with three emergencies. [Results] Our CEEMDAN-BP model could better predict the development trend of online public opinion in emergencies. The average absolute errors of prediction in three emergencies were 8.60%, 17.98% and 11.97%, respectively. Our model’s prediction accuracy and stability were better than the existing ones. [Limitations] The experimental data was based on the daily statistics, which could not fully reflect the changing public opinion. [Conclusions] The CEEMDAN-BP model can effectively predict the development trend of online public opinion in emergencies, which helps related departments to prepare for and manage the emergencies.

Key wordsEmergencies    Online Public Opinion    CEEMDAN    Phase-space Reconstruction    Back Propagation Network
收稿日期: 2021-05-25      出版日期: 2021-08-23
ZTFLH:  C916  
基金资助:*国家社会科学基金项目(17CXW012)
通讯作者: 冯兰萍,ORCID:0000-0003-2334-6621     E-mail: 19941415@hhu.edu.cn
引用本文:   
程铁军, 王曼, 黄宝凤, 冯兰萍. 基于CEEMDAN-BP模型的突发事件网络舆情预测研究*[J]. 数据分析与知识发现, 2021, 5(11): 59-67.
Cheng Tiejun, Wang Man, Huang Baofeng, Feng Lanping. Predicting Online Public Opinion in Emergencies Based on CEEMDAN-BP. Data Analysis and Knowledge Discovery, 2021, 5(11): 59-67.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2021.0525      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2021/V5/I11/59
Fig.1  模型构建流程
Fig.2  三起事件的舆情指数趋势
Fig.3  三起事件舆情指数的CEEMDAN分解结果
参数

事件
新冠肺炎疫情 江苏响水爆炸 长春长生疫苗
τ 3 4 4
m 4 3 3
Table 1  最佳延迟时间及嵌入维数
Fig.4  三起事件的预测结果对比
案例事件 指标 CEEMDAN-BP CEEMDAN-SVM EMD-BP EMD-SVM BP SVM
新冠肺炎疫情 MAPE 8.60% 32.09% 22.86% 37.31% 24.68% 31.57%
PRMSE 9.79% 32.71% 26.08% 37.77% 15.29% 32.17%
TIC 0.047 0.141 0.117 0.160 0.072 0.139
江苏响水爆炸 MAPE 17.98% 89.21% 35.83% 185.12% 22.82% 44.55%
PRMSE 25.87% 93.96% 44.58% 185.09% 25.59% 44.20%
TIC 0.129 0.322 0.190 0.480 0.116 0.181
长春长生疫苗 MAPE 11.97% 30.93% 24.93% 28.95% 28.05% 27.31%
PRMSE 15.30% 33.40% 26.42% 32.20% 32.73% 27.45%
TIC 0.072 0.156 0.150 0.140 0.144 0.121
Table 2  各模型预测性能对比
[1] 中国互联网络信息中心(CNNIC). 第47次中国互联网络发展状况统计报告[EB/OL]. [2021-02-03]. http://cnnic.cn/gywm/xwzx/rdxw/20172017_7084/202102/t20210203_71364.htm.
[1] (China Internet Network Information Center(CNNIC). The 47th China Statistical Report on Internet Development [EB/OL]. [2021-02-03]. http://cnnic.cn/gywm/xwzx/rdxw/20172017_7084/202102/t20210203_71364.htm
[2] 刘果. 新时代网络新闻舆论的时代特征与引导策略[J]. 湖南大学学报(社会科学版), 2019, 33(2):151-156.
[2] (Liu Guo. The Characteristics and Guidance Strategies of the Network News and Public Opinion in the New Era[J]. Journal of Hunan University (Social Sciences), 2019, 33(2):151-156.)
[3] Tsur O, Rappoport A. What’s in a Hashtag? Content based Prediction of the Spread of Ideas in Microblogging Communities[C]// Proceedings of the 5th International Conference on Web Search & Web Data Mining. ACM, 2012.
[4] 罗泰晔. 基于Logistic模型的微博舆情热点发展预测研究[J]. 统计与信息论坛, 2017, 32(10):91-95.
[4] (Luo Taiye. Research on a Prediction Model of the Development of Microblog Hot Topics Based on Logistic Model[J]. Statistics & Information Forum, 2017, 32(10):91-95.)
[5] 徐敏捷. 基于指数平滑法的微博舆情预测模型研究[J]. 中国公共安全(学术版), 2016(1):80-84.
[5] (Xu Minjie. Research on Microblogging Public Opinion Forecast Model Based on Exponential Smoothing[J]. China Public Security(Academy Edition), 2016(1):80-84.)
[6] 滕文杰. 时间序列分析法在突发公共卫生事件网络舆情分析中的应用研究[J]. 中国卫生统计, 2014, 31(6):1071-1073.
[6] (Teng Wenjie. Research on the Prediction of Online Public Opinion base on Time Series[J]. Chinese Journal of Health Statistics, 2014, 31(6):1071-1073.)
[7] 史蕊, 陈福集, 张金华. 基于组合灰色模型的网络舆情预测研究[J]. 情报杂志, 2018, 37(7):105-110.
[7] (Shi Rui, Chen Fuji, Zhang Jinhua. Prediction of Online Public Opinion Based on Combination Grey Model[J]. Journal of Intelligence, 2018, 37(7):105-110.)
[8] 黄亚驹, 陈福集, 游丹丹. 基于混合算法和BP神经网络的网络舆情预测研究[J]. 情报科学, 2018, 36(2):24-29.
[8] (Huang Yaju, Chen Fuji, You Dandan. Research on Network Public Opinion Prediction Based on Hybrid Algorithm and BP Neural Network[J]. Information Science, 2018, 36(2):24-29.)
[9] 游丹丹, 陈福集. 基于改进粒子群和BP神经网络的网络舆情预测研究[J]. 情报杂志, 2016, 35(8):156-161.
[9] (You Dandan, Chen Fuji. Research on the Prediction of Network Public Opinion Based on Improved PSO and BP Neural Network[J]. Journal of Intelligence, 2016, 35(8):156-161.)
[10] 黄敏, 胡学刚. 基于支持向量机的网络舆情混沌预测[J]. 计算机工程与应用, 2013, 49(24):130-134.
[10] (Huang Min, Hu Xuegang. Internet Public Opinion Chaotic Prediction Based on Support Vector Regression Machine[J]. Computer Engineering and Applications, 2013, 49(24):130-134.)
[11] 陈福集, 肖鸿雁. 基于改进ABC-BP模型的网络舆情热度预测研究[J]. 图书馆学研究, 2018(9):84-89.
[11] (Chen Fuji, Xiao Hongyan. Research on the Heat Prediction of Network Public Opinion Based on Improved ABC-BP Model[J]. Research on Library Science, 2018(9):84-89.)
[12] 魏德志, 陈福集, 郑小雪. 基于混沌理论和改进径向基函数神经网络的网络舆情预测方法[J]. 物理学报, 2015, 64(11):52-59.
[12] (Wei Dezhi, Chen Fuji, Zheng Xiaoxue. Internet Public Opinion Chaotic Prediction Based on Chaos Theory and the Improved Radial Basis Function in Neural Networks[J]. Acta Physica Sinica, 2015, 64(11):52-59.)
[13] 高颖. 基于改进混沌理论的网络舆情短期预测策略方法研究[J]. 重庆理工大学学报(自然科学), 2019, 33(6):171-176.
[13] (Gao Ying. Prediction Strategy Method of Short-term Network Public Opinion Based on Improved Chaos Theory[J]. Journal of Chongqing University of Technology (Natural Science), 2019, 33(6):171-176.)
[14] 聂黎生. 基于KPCA-粒子群随机森林算法的舆情趋势预测研究[J]. 现代电子技术, 2019, 42(15):79-82.
[14] (Nie Lisheng. Research on Trend Prediction of Public Opinion Based on KPCA and Particle Swarm Random Forest Algorithm[J]. Modern Electronics Technique, 2019, 42(15):79-82.)
[15] 林育曼, 文海宁, 饶浩. 基于ARIMA-BP神经网络模型的微信舆情热度预测[J]. 统计与决策, 2019, 35(14):71-74.
[15] (Lin Yuman, Wen Haining, Rao Hao. WeChat Public Opinion Heat Forecasting Based on ARIMA-BP[J]. Statistics and Decision, 2019, 35(14):71-74.)
[16] Huang N E, Shen Z, Long S R, et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J]. Proceedings of the Royal Society of London (Series A): Mathematical, Physical and Engineering Sciences, 1998, 454:903-995.
[17] Wu Z, Huang N E. Ensemble Empirical Mode Decomposition: A Noise—Assisted Data Analysis Method[J]. Advances in Adaptive Data Analysis, 2009, 1(1):1-41.
doi: 10.1142/S1793536909000047
[18] Yeh J R, Shieh J S, Huang N E . Complementary Ensemble Empirical Mode Decomposition: A Novel Noise Enhanced Data Analysis Method[J]. Advances in Adaptive Data Analysis, 2010, 2(2):135-156.
doi: 10.1142/S1793536910000422
[19] Torres M E, Colominas M A, Schlotthauer G, et al. A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise[C]// Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2011.
[20] 李亚男, 程志友. 基于CEEMDAN算法及NARX神经网络的短期负荷预测[J]. 安徽大学学报(自然科学版), 2021, 45(2):38-46.
[20] (Li Ya’nan, Cheng Zhiyou. Short Term Load Algorithm Forecasting Based and NARX Neural on CEEMDAN Network[J]. Journal of Anhui University (Natural Science Edition), 2021, 45(2):38-46.)
[21] 林达, 杨招军. 我国股票与基金市场收益和风险的对比分析——基于CEEMDAN[J]. 预测, 2016, 35(1):55-61.
[21] (Lin Da, Yang Zhaojun. A Comparative Analysis of the Risk and Return Between Stocks and Funds-Based on CEEMDAN[J]. Forcasting, 2016, 35(1):55-61.)
[22] Packard N H, Crutchfield J P, Farmer J D. Geometry from a Time Series[J]. Physical Review Letters, 1980, 45(9):712-716.
doi: 10.1103/PhysRevLett.45.712
[23] Takens F. Detecting Strange Attractors in Turbulence[J]. Lecture Notes in Mathematics, 1981, 898:366-381.
[1] 范涛,王昊,吴鹏. 基于图卷积神经网络和依存句法分析的网民负面情感分析研究*[J]. 数据分析与知识发现, 2021, 5(9): 97-106.
[2] 尹浩然,曹金璇,曹鲁喆,王国栋. 扩充语义维度的BiGRU-AM突发事件要素识别研究*[J]. 数据分析与知识发现, 2020, 4(9): 91-99.
[3] 邓建高,张璇,傅柱,韦庆明. 基于系统动力学的突发事件网络舆情传播研究:以“江苏响水爆炸事故”为例*[J]. 数据分析与知识发现, 2020, 4(2/3): 110-121.
[4] 梁艳平,安璐,刘静. 同类突发公共卫生事件微博话题共振研究*[J]. 数据分析与知识发现, 2020, 4(2/3): 122-133.
[5] 丁晟春,俞沣洋,李真. 网络舆情潜在热点主题识别研究*[J]. 数据分析与知识发现, 2020, 4(2/3): 29-38.
[6] 黄微,赵江元,闫璐. 网络热点事件话题漂移指数构建与实证研究*[J]. 数据分析与知识发现, 2020, 4(11): 92-101.
[7] 何振宇,董祥祥,朱庆华. 基于用户使用行为视角的百度百科词条分类研究*[J]. 数据分析与知识发现, 2019, 3(6): 117-122.
[8] 梅妍霜,朱恒民,魏静. 媒体协同对网络舆情扩散的作用机制研究*[J]. 数据分析与知识发现, 2019, 3(2): 65-71.
[9] 胡哲,查先进,严亚兰. 突发事件情境下在线健康社区用户交互行为研究 *[J]. 数据分析与知识发现, 2019, 3(12): 10-20.
[10] 李纲,陈思菁,毛进,谷岩松. 自然灾害事件微博热点话题的时空对比分析 *[J]. 数据分析与知识发现, 2019, 3(11): 1-15.
[11] 贾隆嘉, 张邦佐. 高校网络舆情安全中主题分类方法研究*——以新浪微博数据为例[J]. 数据分析与知识发现, 2018, 2(7): 55-62.
[12] 王璟琦, 李锐, 吴华意. 基于空间自相关的网络舆情话题演化时空规律分析*[J]. 数据分析与知识发现, 2018, 2(2): 64-73.
[13] 武玉英, 孙平, 何喜军, 蒋国瑞. 新能源领域专利转让加权网络中主体间技术交易机会预测*[J]. 数据分析与知识发现, 2018, 2(11): 73-79.
[14] 李真, 丁晟春, 王楠. 网络舆情观点主题识别研究*[J]. 数据分析与知识发现, 2017, 1(8): 18-30.
[15] 王晰巍, 张柳, 李师萌, 王楠阿雪. 新媒体环境下社会公益网络舆情传播研究* ——以新浪微博“画出生命线”话题为例[J]. 数据分析与知识发现, 2017, 1(6): 93-101.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn