基于贝叶斯网络的智能舆情分析监控技术研究  

Research on intelligent public opinion analysis and monitoring technology based on Bayesian network

作　　者：杨寒冰 王春玲[1] YANG Hanbing;WANG Chunling(Xi’an Vocational and Technical College of Aeronautics and Astronautics,Xi’an 710089,China)

机构地区：[1]西安航空职业技术学院,陕西西安710089

出　　处：《电子设计工程》2021年第10期73-76,81,共5页Electronic Design Engineering

基　　金：中华职业教育社2020年重点调研课题子课题(ZJS20200563);陕西省2018年教育厅科研计划项目(18JK0413)。

摘　　要：针对社交网络信息传播速度快,容易造成负面情绪大面积传播引发网络舆情的问题,文中进行了智能舆情分析监控技术的研究。通过使用朴素贝叶斯网络作为情感倾向分类器,并与堆叠降噪自编码器相融合,构建了智能舆情分析监控模型。将社交网络上的文本信息进行预处理,通过与情感词典比对进行分词,同时使用TF-IDF算法计算特征权重并构成词向量。将词向量输入至智能舆情分析监控模型中进行情感倾向分析。对比实验结果表明,文中所述方案比使用Softmax分类器的模型具有更高的准确率,尤其是在处理高纬度词向量的情况下,其准确率有较显著的提高。In view of the problem that social network information spreads fast and easily causes negative emotions to spread in a large area,this paper studies the intelligent public opinion analysis and monitoring technology.By using naive Bayesian network as sentiment tendency classifier and combining with stack noise reduction self encoder,an intelligent public opinion analysis and monitoring model is constructed.The text information on social network is preprocessed,and words are segmented by comparing with emotion dictionary.At the same time,TF⁃IDF algorithm is used to calculate the feature weight to form word vector.The word vector is input into the intelligent public opinion analysis monitoring model to analyze the emotional tendency.The experimental results show that the proposed scheme has a higher accuracy than the model using Softmax classifier,especially when dealing with high latitude word vectors.

关 键 词：智能舆情分析监控技术 朴素贝叶斯网络 堆叠降噪自编码器 情感词典 TF-IDF算法 

分 类 号：TN98[电子电信—信息与通信工程] TP183[自动化与计算机技术—控制理论与控制工程]