Through the Scrapy framework,the relevant Weibo blog posts and comments related to earthquake of magnitude 5.0 or above in China in the past three years (2021-2023) were obtained,and the crawled text data was preprocessed and compiled into a dataset,and a deep learning earthquake public opinion sentiment tendency model based on BERT and Long Short-Term Memory (LSTM) was designed. The results show that the accuracy of the model in the text sentiment analysis of earthquake public opinion reaches 97.8％,and it has efficient feature extraction ability,which can provide a reference for the monitoring of earthquake network public opinion.
关键词
Scrapy框架/地震舆情/BERT/LSTM/情感分析
Key words
Scrapy framework/earthquake public opinion/BERT/LSTM/sentiment analysis
维普
万方数据