【摘要】 针对现有的舆情传播模型研究与实际舆情数据结合较少以及难以从舆情大数据中挖掘舆情传播内在规律的问题,提出一种基于实际网络舆情大数据采用神经网络的舆情传播模型参数反演算法。改进经典SIR传染病传播模型,构建一种网络舆情传播模型,基于该模型对实际案例进行参数反演,预测网络舆情的后续传播趋势,并与马尔可夫预测模型对比,所提算法可以精确预测舆情的具体热度值。实验结果表明,所提算法在预测性能上具有一定的优越性,可以用于网络突发事件传播的数据拟合、过程模拟和趋势预测。更多还原

【Abstract】 Concerning that the existing researches on public opinion propagation model are seldom combined with the practical opinion data and digging out the inherent law of public opinion propagation from the opinion big data is becoming an urgent problem, a parameter inversion algorithm of public opinion propagation model using neural network was proposed based on the practical opinion big data. A network opinion propagation model was constructed by improving the classical disease spreading Susceptible-Infective-Recovered(SIR) model. Based on this model, the parameter inversion algorithm was used to predict the network public opinion’s trend of actual cases. The proposed algorithm could accurately predict the specific heat value of public opinion compared with Markov prediction model. The experimental results show that the proposed algorithm has certain superiority in prediction and can be used for data fitting, process simulation and trend prediction of network emergency spreading.更多还原