Network patriotism public opinion event tracking, predicting and dredging method
A network patriotism public opinion event tracking, predicting and dredging method comprises the steps that firstly, a web crawler system is used for crawling hot news websites and social media of thewhole network, whether topics are related to patriotism or not is judged through a BERT model, and t...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
19.05.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | A network patriotism public opinion event tracking, predicting and dredging method comprises the steps that firstly, a web crawler system is used for crawling hot news websites and social media of thewhole network, whether topics are related to patriotism or not is judged through a BERT model, and the popularity of the topics in the whole network is calculated; the system recognizes an emergencyhotspot event through an LOF algorithm and continuously tracks the event. A deep learning method combining a long-term and short-term memory (LSTM) network and a convolutional neural network (CNN) isused, and static attributes and dynamic attributes are combined to predict the popularity trend of public opinions by using a deep neural network. According to a neural network trained by using similar historical event data, the system can give a reference response scheme for a user to dredge public opinions, and predict a public opinion popularity change trend after the scheme is used. Accordingto the invention, public opi |
---|---|
Bibliography: | Application Number: CN201911238120 |