摘要
随着互联网技术的发展,越来越多人习惯通过网络表达看法和观点.然而网络上言论鱼龙混杂,学生作为使用网络的一个主要群体,思想还不够成熟,很容易受一些负面情绪的影响,对此,实时掌握网络舆情,有针对性地进行正确引导具有重要意义.文章提出并实现了一个基于LSTM-CNN混合模型的舆情分析系统.该系统通过网络爬虫实时获取舆情信息,通过LSTM-CNN混合模型可以实时掌握学生关注的话题和舆论热点,实时了解学生的思想动态.实验结果表明:所建立的混合模型的分类正确率较单一模型高,系统具有实时性和准确性的特点,在实际应用中有指导意义.
With the development of internet technology,more and more people are used to express their opinions in the network environment.However,some comments on the network are mixed.As a major group of network user,students'thoughts are not mature enough,who are easily affected by some negative emotions.Therefore,it is of great significance to master the network public opinion in real time and guide it correctly.This paper presents a public opinion analysis system based on LSTM-CNN hybrid model.The system can get the public opinion information in real time by the web crawler.Through the LSTM-CNN hybrid model,it can grasp the topics and hot spots of public opinion that students pay close attention to in real time,and get the ideological trends of students in time.The experimental results show that the classification accuracy of the hybrid model is higher than the single models,and the system has the characteristics of real-time and accuracy,which has guiding significance in practical applications.
作者
黄迅
孙军梅
HUANG Xun;SUN Junmei(School of Information Science and Engineering,Hangzhou Normal University,Hangzhou 311121,China)
出处
《杭州师范大学学报（自然科学版）》
CAS
2020年第4期427-431,共5页
Journal of Hangzhou Normal University(Natural Science Edition)
基金
杭州市科技计划项目(20170533B04).
关键词
深度学习
舆情分析
神经网络
网络爬虫
deep learning
public opinion analysis
neural network
internet crawler
