基于新陈代谢GM(1,N)马尔科夫模型的动态网络舆情危机预测

Dynamic Network Public Opinion Crisis Prediction Based on Metabolic GM(1,N) Markov Model

【目的/意义】随着信息通信技术的迅猛发展,网络舆情的社会影响力越来越大,提高网络舆情预警的精确度、舆情信息监测的科学性,有助于相关舆情管理部门对舆情信息进行有效引导。【方法/过程】通过分析影响网络舆情危机的相关因素,采用GM(1,N)进行预测,并对结果进行残差修正,在此基础上,利用马尔科夫模型进行二次修正,最后依据新陈代谢的思想进行数据的新旧更替,建立GM(1,N)马尔科夫动态模型。【结果/结论】结果显示,舆情危机热度预测属于典型的灰色系统研究,通过与其他模型的对比分析可得构建的新陈代谢GM(1,N)马尔科夫动态预测模型精确度更高,是一种有效的舆情危机热度预测方法。

【Purpose/significance】With the rapid development of information and communication technology,the social influence of network public opinion is increasing.To improve the accuracy of network public opinion early warning and the scientific monitoring of public opinion information is helpful for the relevant public opinion management departments to guide the public opinion information effectively.【Method/process】By analyzing the related factors that affect the network public opinion crisis,the GM(1,N)is used for the prediction,and the residual correction is carried out on the result.On the basis,the second residual correction is carried out by using the Markov model.Finally,according to the idea of metabolism,the new and old replacement of data is carried out,and the dynamic model of GM(1,N)Markov is established.【Result/conclusion】The results show that the prediction of the heat of public opinion crisis is a typical grey system study.By comparing with other models,the proposed GM(1,N)Markov dynamic model has higher prediction accuracy.It is an effective method for predicting the heat of public opinion crisis.