新媒体环境下突发环境事件网络舆情风险信息感知模型

Information Perception Model of Network Public Opinion Risk ofEnvironmental Emergencies in New Media Environment

[目的/意义]网络舆情风险信息涉及要素较多,为了提高网络舆情风险信息感知效果,在新媒体环境下构建了突发环境事件网络舆情风险信息感知模型。[方法/过程]建立突发环境事件网络舆情信息流风险指标集,赋予评价指标权重,对权重离散化处理,构成相似系数矩阵。通过舆情主体建模、舆情信息模型建立与网民情感模型建立3个部分分析网络舆情传播核心要素演化规律。在此基础上计算传播概率,确定用户传播信息的涉入程度,采用Logistic回归模型感知风险信息风险高低。采用决策树对舆情风险预警,实现突发环境事件网络舆情风险信息感知。[结果/结论]实验结果表明,所构建模型应用后的事件舆情情感演化情况分析准确性较高,各个事件的转发数量和恶意评论数量感知准确度较高,预警效果更好,有效提高了突发环境事件网络舆情风险信息感知效果。

[Purpose/Significance]Network public opinion risk information involves many elements.In order to improve the perception effect of network public opinion risk information,a network public opinion risk information perception model of environmental emergencies is constructed in the new media environment.[Method/Process]The risk index set of network public opinion information flow of environmental emergencies was established,the evaluation index weight was given,and the weight was discretized to form a similarity coefficient matrix.This paper analyzed the evolution law of the core elements of network public opinion communication through three parts:the modeling of public opinion subject,the establishment of public opinion information model and the establishment of Internet users emotion model.On this basis,the propagation probability was calculated to determine the involvement degree of users in disseminating information,and the risk of information was perceived by logistic regression model.The decision tree was used for public opinion risk early warning to realize the network public opinion risk information perception of environmental emergencies.[Result/Conclusion]The experimental results show that the analysis accuracy of the event public opinion emotion evolution after the application of the constructed model is higher,the perception accuracy of the number of forwarding and malicious comments of each event is higher,and the early warning effect is better,which effectively improves the perception effect of network public opinion risk information of environmental emergencies.