基于信息传播模型-SIR传染病模型的社交网络舆情传播动力学模型研究

Research on the Communication Dynamics Model of Social Network Public Opinion Based on the SIS Model

【目的/意义】随着移动网络技术的飞速发展,用户已习惯在社交网络平台发表意见,进而形成所谓的网络舆情。准确建立舆情的传播模型,对于舆情的引导和控制具有重要的帮助。【方法/过程】本文基于传统的SIR传染病模型,综合考虑用户的心理特征行为因素,搭建新型的社交网络舆情传播动力学模型,并选用粒子群算法,以2016年内热点的微博舆情事件为例,求解模型参数的最优值,并进行实验数据验证。【结果/结论】结果表明:用户的追根溯源心理、持续关注心理以及漠不关心心理等心理特征对舆情的传播特性有重要影响,同时本文给出的模型由于考虑了用户的心理特征行为因素,模型的准确性相较传统的SIR模型有明显优势,模型拟合曲线与真实数据曲线基本一致,并且模型拟合值与真实数据的绝对误差值和RMSE值都较低。本文的研究对准确预测舆情信息传播趋势以及舆情的分析和引导有着重要的指导作用。

[Purpose/significance] With the rapid development of mobile network technology, users have been accustomed to expressed views in the social network platform which leads to the formation of the so-called network public opinion. To construct the spread model of public opinion accurately is helpful to lead and control it. [Method/process] Based on the traditional SIR epidemic model, this paper constructs a new dynamic model of social network public opinion communica- tion via the Particle Swarm Optimization Algorithm to solve the optimal value of the model parameters. With the analysis of last year＇s hot microblogging public opinion event, experimental data is verified. [Result/conclusion] The results show that the psychological characteristics of users such as tracing to the source,continuous attention and indifferent have important influence to the spread of public opinion. Because the model is based on the psychological characteristics and behavioral factors of the users, compared with the traditional SIR model, it has obvious accuracy advantages. The model fitting curve and the real data curve is basically the same, the model fitting value and RMSE values of the data are low. The research re- suits has important guiding function to predict the spread trend of public opinion accurately.