突发事件网络舆情风险预警模型研究  

Research on Risk Early Warning Model of Emergent Network Public Opinion

作　　者：徐建国 刘梦凡 刘泳慧 XU Jian-guo;LIU Meng-fan;LIU Yong-hui(College of Computer Science and Engineering,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]山东科技大学计算机科学与工程学院,山东青岛266590

出　　处：《软件导刊》2020年第7期70-75,共6页Software Guide

基　　金：青岛市哲学社会科学规划项目(QDSKL1601121)。

摘　　要：增强突发事件研判、预警与快速响应能力,对加强网络舆情监管与引导,维护社会安全和稳定具有重要意义。首先基于网络舆情演化机制与特征建立科学、合理的指标体系;然后选取重要程度与分类性能均比较优异的末级指标作为特征属性,构造C4.5决策树风险预警模型;最后将突发事件网络舆情相关数据带入风险预警模型,得到预警风险等级。实验结果表明,该方法能够对突发事件网络舆情进行风险预警,预警准确率高达94.7%。It is of great significance to strengthen the supervision and guidance of network public opinion and maintain social security and stability by strengthening the ability to judge,warn and respond quickly.First,a scientific and reasonable index system is established based on the evolution mechanism and characteristics of network public opinion,and then the last-level indicators that have excellent importance and classification performance are selected as feature attributes to construct a C4.5 decision tree risk early warning model.Finally,the data related to the emergent network public opinion is brought into the risk early warning model to obtain the early warning risk level.The experimental results show that this method can give correct risk early warning to emergency public opinion,and the early warning accuracy rate is as high as 94.7%.

关 键 词：突发事件 网络舆情 风险预警 C4.5决策树 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]