基于改进粒子群和BP神经网络的网络舆情预测研究  

Research on the Prediction of Network Public Opinion Based on Improved PSO and BP Neural Network

作　　者：游丹丹[1] 陈福集[1] 

机构地区：[1]福州大学经济与管理学院,福州350108

出　　处：《情报杂志》2016年第8期156-161,共6页Journal of Intelligence

基　　金：国家自然科学基金项目"基于知识网格面向网络舆情的政府决策知识供需匹配研究"(编号:71271056)

摘　　要：[目的/意义]网络舆情是一种复杂、多变的系统,通过数据分析并建立网络舆情预测模型来预测其发展趋势具有一定的研究意义。[方法/过程]选择热点话题的百度指数作为网络舆情趋势预测的时间序列指标,采用粒子群算法和BP神经网络算法构建了基于改进粒子群算法和BP神经网络的网络舆情预测模型,并结合天津港爆炸事件案例进行验证与分析。[结果/结论]实验结果表明该模型在预测的性能上具有一定的优越性,为网络舆情预测提供了一有效模型。[ Purpose/Significance] Network public opinion is a complex and changeable system, it is significant to predict its tendency accurately based on data analysis and establishing prediction model of network public opinion. [ Method/Process ] The paper selects the Baidu index of hot topics as the index of time series for predicting the trend of network public opinion, employing Particle Swarm Optimization and BP neural network to construct the prediction model based on improved particle swarm algorithm and BP neural network, and then verifies and analyzes the experimental results combined with the case of Tianjin explosion. [ Result/Conclusion] The results show that the model has certain superiority in prediction and provides an effective model for the prediction of network public opinion.

关 键 词：网络舆情 网络舆情预测 粒子群算法 BP神经网络 

分 类 号：G350[文化科学—情报学] G203