Please wait a minute...
Data Analysis and Knowledge Discovery  2021, Vol. 5 Issue (4): 37-48    DOI: 10.11925/infotech.2096-3467.2020.0838
Current Issue | Archive | Adv Search |
Predicting of Public Opinion Reversal with Improved SMOTE Algorithm and Ensemble Learning
Wang Nan,Li Hairong,Tan Shuru()
School of Management Science and Information Engineering, Jilin University of Finance and Economics, Changchun 130117, China
Download: PDF (1880 KB)   HTML ( 11
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper analyzes online public opinion events to determine their attributes and classification. When an online public opinion event occurs, we can predict whether it will reverse in advance. This study not only helps the governments adjust the direction of public opinion in time but also protect the credibility of the governments and media. [Methods] First, we retrieved representative online public opinion events from the past five years. Then, we used the improved SMOTE algorithm to conduct a balance distribution treatment on the data set. Third, we built a prediction model for online public opinion reversal based on the neural network ensemble learning. Finally, we evaluated the model’s performance and internal mechanism with online public opinion events from 2020. [Results] The accuracy of the proposed model reached 99% and the F and AUC values were both 0.99. [Limitations] We only chose some characteristics from public opinion reversal events. Therefore, it cannot comprehensively represent all reversal events occurring in the future. [Conclusions] The constructed model can accurately predict whether or not a public opinion event will reverse.

Key wordsOnline Public Opinion Reversal      SMOTE Algorithm      Neural Network      Ensemble Learning      Empirical Study     
Received: 26 August 2020      Published: 21 December 2020
ZTFLH:  分类号: G353  
Fund:Jilin Provincial Department of Education “Thirteenth Five Year Plan” Science and Technology Research Project(JJKH20210131KJ);Key Project of “Thirteenth Five Year Plan” of Jilin Province Education Science(ZD20024);National Natural Science Foundation of China(61702213)
Corresponding Authors: Tan Shuru     E-mail: 1070929014@qq.com

Cite this article:

Wang Nan,Li Hairong,Tan Shuru. Predicting of Public Opinion Reversal with Improved SMOTE Algorithm and Ensemble Learning. Data Analysis and Knowledge Discovery, 2021, 5(4): 37-48.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2020.0838     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2021/V5/I4/37

Construction of Online Public Opinion Reversal Identification Model
New Sample Distribution Generated by Improved SMOTE Algorithm
Single Neural Network Model(Individual Learner)
舆情反转事件 舆情非反转事件
陕西榆林产妇跳楼案 西安奔驰女司机维权事件 河南开封通许再曝28名村医集体辞职 “冰花男孩”走红
小学生自带桌板地铁赶作业 周口男婴丢失案 广东一女孩搭摩的被杀害 “河间驴肉”黑作坊造假
红黄蓝幼儿园虐童案 黑龙江男子赵宇福州见义勇为案 江苏徐州机场内飞机被吹跑 女博士举报北航教授陈小武性骚扰
00后CEO狂怼成年人事件 安徽女子称遭“奸杀”威胁 河南一女子醉驾玛莎拉蒂致两死 长沙民警棒杀金毛引网友“声讨”
女子扒高铁门事件 女子网购18件衣服旅拍后退货 湖南益阳教师李尚平举报腐败被枪杀案 北林大四名女生去雪乡途中遇车祸身亡
鸿茅药酒事件 网红摆拍捡垃圾 网曝北京早高峰地铁多人席地而坐 上海地铁一男子跳入轨道被列车冲撞身亡
高考答题卡被掉包 重庆公交车坠江事件 老太向发动机投硬币致航班延误 证监会官司打输:责令答复顾雏军
王风雅小朋友去世事件 成都女司机被打事件 上海一老人立遗嘱遗产给女儿1元 考研数学被指现“神押题”疑发生泄题
网红saya殴打孕妇 大学生救落水儿童溺亡事件 网曝主播为拍段子让智障人士互殴 南昌大学一副院长被指长期性侵女生
Case of Online Public Opinion Events
Feature Assignment Basis
指标名 含义 计算公式
准确率 分类模型所有预测正确的结果占总观测值的比重 Accuracy=TP+TNTP+FP+FN+TN
精确率 模型预测是正例的所有结果中,模型预测正确的比重 Precision=TPTP+FP
召回率 真实值是正例的所有结果中,模型预测正确的比重 Recall=TPTP+FN
特异度 真实值是反例的所有结果中,模型预测正确的比重 Specificity=TNTN+FP
F PrecisionRecall加权调和平均数,并假设两者一样重要 F1-Score=2Precision·RecallPrecision+Recall
Partial Indexes of the Classification Model Evaluation
评估指标 准确率 精确率 召回率 特异度 F
数值 0.99 0.98 1.00 0.99 0.99
Evaluation Index Values
ROC Curve of Integrated Neural Network Classification Model
案例 真实值 预测值
4月29日北京市延庆区医院伤医事件 0 0
官方通报班主任给女生发暧昧信息 0 0
西安苏福记一厨师向锅里吐口水 0 0
湖南张家界天门山翼装飞行女生身亡 0 0
中国成功发射第54颗北斗卫星 0 0
双黄连口服液可抑制新型冠状病毒事件 1 1
丈夫实名举报妻子婚内出轨绿地高管 1 1
Comparison Between the Real Situation and the Predicted Situation
Stage Division and Basic Trend of “Novel Coronavirus Can be Inhibited by Shuang Huanglian Oral Liquid” Event
Matrix Thermal Diagram of Correlation Coefficients
[1] 中国互联网信息中心. 第45次中国互联网络发展状况统计报告[R/OL].[ 2020- 6- 12]. http://www.cac.gov.cn/2020-04/27/c_1589535470378587.htm.
[1] ( China Internet Network Information Center. The 45th China Statistical Report on Internet Development[R/OL]. [ 2020- 6- 12]. http://www.cac.gov.cn/2020-04/27/c_1589535470378587.htm.
[2] 布署. 全媒体语境下对“舆情反转新闻常态化”的反思[J]. 传媒, 2020(3):94-96.
[2] ( Bu Shu. Reflection on the “Normalization of Public Opinion Reversal News” in the Context of All Media[J]. Media, 2020(3):94-96.)
[3] 黎勇. 舆情反转:一种反向的群体极化[J]. 青年记者, 2019(7):42-44.
[3] ( Li Yong. Public Opinion Reversal: A Kind of Reverse Group Polarization[J]. Youth Journalist, 2019(7):42-44.)
[4] 林榕, 郭华君. 网络舆情反转的构成、机理探析[J]. 传播力研究, 2019,3(20):280.
[4] ( Lin Rong, Guo Huajun. A Study on the Composition and Mechanism of Internet Public Opinion Reversal[J]. Research on Transmission Competence, 2019,3(20):280.)
[5] Proietti C. The Dynamics of Group Polarization[C]// Proceedings of International Workshop on Logic, Rationality and Interaction. 2017: 195-208.
[6] 孙翠平. 网络舆情反转的传播及演化研究[D]. 广州: 华南理工大学, 2018.
[6] ( Sun Cuiping. A Study on the Spread and Evolution of Internet Public Opinion Reversal[D]. Guangzhou: South China University of Technology, 2018.)
[7] 夏一雪, 兰月新, 刘茉, 等. 大数据环境下网络舆情反转机理与预测研究[J]. 情报杂志, 2018,37(8):92-96, 207.
[7] ( Xia Yixue, Lan Yuexin, Liu Mo, et al. Inversion Mechanism and Prediction of Network Public Opinion in Big Data Environment[J]. Journal of Intelligence, 2018,37(8):92-96, 207.)
[8] 汪明艳, 余丽彬, 胡华. 基于行为意愿与反转信息可靠性的舆论反转演变研究[J]. 情报杂志, 2019,38(4):125-131.
[8] ( Wang Mingyan, Yu Libin, Hu Hua. The Research on Reverse Evolution of Public Opinion Based on Behavioral Intention and Reliability of Reverse Information[J]. Journal of Intelligence, 2019,38(4):125-131.)
[9] 田俊静, 兰月新, 夏一雪, 等. 基于决策树方法的网络舆情反转识别与实证研究[J]. 情报杂志, 2019,38(8):121-125, 171.
[9] ( Tian Junjing, Lan Yuexin, Xia Yixue, et al. Recognition and Empirical Study of Network Public Opinion Reversal Based on Decision Tree Method[J]. Journal of Intelligence, 2019,38(8):121-125, 171.)
[10] 田世海, 孙美琪, 张家毓. 基于贝叶斯网络的自媒体舆情反转预测[J]. 情报理论与实践, 2019,42(2):127-133.
[10] ( Tian Shihai, Sun Meiqi, Zhang Jiayu. Prediction of We-media Public Opinion Reversion Based on Bayesian Network[J]. Information Studies: Theory & Application, 2019,42(2):127-133.)
[11] 蒋叶莎. 后真相时代真相何以接近真实——基于成都七中实验学校食品安全事件的舆情分析[J]. 东南传播, 2019(10):91-93.
[11] ( Jiang Yesha. How the Truth Approaches the Truth in the Post-truth Era-An Analysis of Public Opinion Based on the Food Safety Incident in Chengdu No.7 Experimental School[J]. Southeast Communication, 2019(10):91-93.)
[12] 宋凯, 袁奂青. 后真相视角中的网民情绪化传播[J]. 现代传播(中国传媒大学学报), 2019,41(8):146-150, 156.
[12] ( Song Kai, Yuan Huanqing. The Emotional Communication of Internet Users from the Perspective of Post-truth[J]. Modern Communication (Journal of Communication University of China), 2019,41(8):146-150, 156.)
[13] 谭艳霞, 化存才. 网络舆情反转问题的模糊聚类分析[J]. 云南大学学报(自然科学版), 2019,41(S1):16-20.
[13] ( Tan Yanxia, Hua Cuncai. Analysis of Cluster on the Inversion Problem of Network Public Opinion Events[J]. Journal of Yunnan University (Natural Science Edition), 2019,41(S1):16-20.)
[14] 詹婷. 热点事件中的舆论反转路径研究[D]. 哈尔滨: 黑龙江大学, 2017.
[14] ( Zhan Ting. Research on the Path of Public Opinion Reversal in Hot Issues[D]. Harbin: Heilongjiang University, 2017.)
[15] 张春颜, 刘煊. 后真相视角下网络舆论反转的主体行为、情境类型与规避策略分析[J]. 学习论坛, 2019(7):58-63.
[15] ( Zhang Chunyan, Liu Xuan. Analysis on the Subject Behavior, Situation Types and Avoidance Strategies of the Network Public Opinion Reversal From the Post-truth Perspective[J]. Tribune of Study, 2019(7):58-63.)
[16] 鲜宁, 蒋睿萍, 张静. 自媒体时代网络募捐的优化途径——以“小凤雅”事件为例[J]. 新闻知识, 2019(4):59-62.
[16] ( Xian Ning, Jiang Ruiping, Zhang Jing. The Optimized Way of Network Fund-raising in the Age of We-media-Taking the Case of “Xiao Fengya” as an Example[J]. News Research, 2019(4):59-62.)
[17] 王璐瑶. 网络舆情博弈中的舆情反转研究——以“王凤雅事件”为例[J]. 新闻前哨, 2019(4):43.
[17] ( Wang Luyao. Research on Public Opinion Reversal in Online Public Opinion Game-Taking the “Wang Fengya Event”as an Example[J]. Press Outpost, 2019(4):43.)
[18] 金林, 毛浩. 农民工社会角色的媒体框架构建[J]. 中国青年研究, 2008(11):54-57.
[18] ( Jin Lin, Mao Hao. Construction of Media Framework of Social Roles of Migrant Workers[J]. China Youth Study, 2008(11):54-57.)
[19] 郝永华, 芦何秋. 风险事件的框架竞争与意义建构——基于“毒胶囊事件”新浪微博数据的研究[J]. 新闻与传播研究, 2014,21(3):20-33.
[19] ( Hao Yonghua, Lu Heqiu. Framework Competition and Meaning Construction of Risk Events - A Study Based on Sina Weibo Data of “Toxic Capsule Event”[J]. Journalism & Communication, 2014,21(3):20-33.)
[20] 王正祥. 反转新闻的“病理”特征与角色失范探讨——基于51个反转新闻样本的统计分析[J]. 天水师范学院学报, 2016,36(6):95-100.
[20] ( Wang Zhengxiang. Discussion on “Pathological” Characteristics and Role Anomia of Reversal News-A Statistical Analysis Based on 51 Reversal News Samples[J]. Journal of Tianshui Normal University, 2016,36(6):95-100.)
[21] 杨峥嵘. 后真相时代下的舆情反转和传媒自律[J]. 传播力研究, 2019,3(20):37,39.
[21] ( Yang Zhengrong. Public Opinion Reversal and Media Self-discipline in the Post-truth Era[J]. Research on Transmission Competence, 2019,3(20):37,39)
[22] Jud C M, Park B. Definition and Assessment of Accuracy in Social Stereotypes[J]. Psychological Review, 1993,100(1):109-128.
doi: 10.1037/0033-295X.100.1.109
[23] 董方玉. 民间引爆网络事件的舆情特点——以“北电性侵事件”为例[J]. 新闻传播, 2018(21):45-48.
[23] ( Dong Fangyu. The Characteristics of Public Opinion of Network Events Triggered by Civil Society-Taking the “Sexual Assault at Nortel” as an Example[J]. Journalism Communication, 2018(21):45-48.)
[24] Stoner J A F. A Comparison of Individual and Group Decisions Involving Risk[D]. Cambridge: University of Cambridge, 1961.
[25] 刘茜. 网络群体极化现象定量研究——基于新浪微博的个案分析[D]. 北京: 清华大学, 2011.
[25] ( Liu Qian. Quantitative Research on Network Group Polarization Phenomenon-A Case Analysis Based on Sina Twitter[D]. Beijing: Tsinghua University, 2011.)
[26] 麦克斯韦尔·麦考姆斯, 郭镇之 邓理峰. 议程设置理论概览: 过去, 现在与未来[J]. 新闻大学, 2007(3):55-67.
[26] ( Maxwell McCombs, Guo Zhenzhi, Deng Lifeng. A Look at Agenda-Setting: Past, Present and Future[J]. Journalism Quarterly, 2007(3):55-67.)
[27] 毕宏音, 田华. 舆情“类反转”现象分析与反思——以“万州公交车坠江事件”为例[J]. 情报杂志, 2019,38(7):103-110.
[27] ( Bi Hongyin, Tian Hua. Analysis and Reflection on the Phenomenon of “Quasi-reversal” in Public Opinion-Taking the “Wanzhou Bus Falling into the River Incident” as an Example[J]. Journal of Intelligence, 2019,38(7):103-110.)
[1] Qiu Yunfei, Guo Lei. Predicting Diabetic Complications with Unbalanced Data[J]. 数据分析与知识发现, 2021, 5(2): 116-128.
[2] Li Danyang, Gan Mingxin. Music Recommendation Method Based on Multi-Source Information Fusion[J]. 数据分析与知识发现, 2021, 5(2): 94-105.
[3] Yin Haoran,Cao Jinxuan,Cao Luzhe,Wang Guodong. Identifying Emergency Elements Based on BiGRU-AM Model with Extended Semantic Dimension[J]. 数据分析与知识发现, 2020, 4(9): 91-99.
[4] Qiu Erli,He Hongwei,Yi Chengqi,Li Huiying. Research on Public Policy Support Based on Character-level CNN Technology[J]. 数据分析与知识发现, 2020, 4(7): 28-37.
[5] Liu Weijiang,Wei Hai,Yun Tianhe. Evaluation Model for Customer Credits Based on Convolutional Neural Network[J]. 数据分析与知识发现, 2020, 4(6): 80-90.
[6] Wang Mo,Cui Yunpeng,Chen Li,Li Huan. A Deep Learning-based Method of Argumentative Zoning for Research Articles[J]. 数据分析与知识发现, 2020, 4(6): 60-68.
[7] Yan Chun,Liu Lu. Classifying Non-life Insurance Customers Based on Improved SOM and RFM Models[J]. 数据分析与知识发现, 2020, 4(4): 83-90.
[8] Su Chuandong,Huang Xiaoxi,Wang Rongbo,Chen Zhiqun,Mao Junyu,Zhu Jiaying,Pan Yuhao. Identifying Chinese / English Metaphors with Word Embedding and Recurrent Neural Network[J]. 数据分析与知识发现, 2020, 4(4): 91-99.
[9] Xu Yuemei,Liu Yunwen,Cai Lianqiao. Predicitng Retweets of Government Microblogs with Deep-combined Features[J]. 数据分析与知识发现, 2020, 4(2/3): 18-28.
[10] Xiang Fei,Xie Yaotan. Recognition Model of Patient Reviews Based on Mixed Sampling and Transfer Learning[J]. 数据分析与知识发现, 2020, 4(2/3): 39-47.
[11] Ni Weijian,Guo Haoyu,Liu Tong,Zeng Qingtian. Online Product Recommendation Based on Multi-Head Self-Attention Neural Networks[J]. 数据分析与知识发现, 2020, 4(2/3): 68-77.
[12] Feng Wengang,Jiang Zhaofeifan. Improving Security Checks and Passenger Risk Evaluation with Classification of Airline Passengers[J]. 数据分析与知识发现, 2020, 4(12): 105-119.
[13] Yu Bengong,Ji Haomin. Semi-Supervised Method for Text Classification Based on DW-TCI[J]. 数据分析与知识发现, 2020, 4(10): 58-69.
[14] Tao Yue,Yu Li,Zhang Runjie. Active Learning Strategies for Extracting Phrase-Level Topics from Scientific Literature[J]. 数据分析与知识发现, 2020, 4(10): 134-143.
[15] Bengong Yu,Yumeng Cao,Yangnan Chen,Ying Yang. Classification of Short Texts Based on nLD-SVM-RF Model[J]. 数据分析与知识发现, 2020, 4(1): 111-120.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn