Abstract
Comments on Sina Weibo are one of the main ways for users to interact and give feedback when viewing Weibo content. Some comments may use emotional language to guide public emotions and attitudes, and gather together to form an atmosphere of public opinion. In recent years, deep learning has made great progress and has been widely used in natural language processing to solve problems such as sentiment analysis, question and answer systems, and speech recognition. This article takes the recent ChatGPT popular out-of-circle event as an example. It uses Python to crawl the comment data in related Weibo, and analyzes netizens' emotional attitude towards the event and its positive and negative classification based on the BiLSTM model. Realize the emotional analysis of netizens on the event so as to grasp the public opinion situation of the network in a timely manner.