Network patriotism public opinion event tracking, predicting and dredging method

• Main Authors: LAN HANLIN, CHEN ZHONGTIAN, CHEN HANCONG, WANG WENHUAN
• Format: Patent
• Language: Chinese; English
• Published: 19.05.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

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