A Study on Sentiment Visual Analysis of Educational Public Opinion Based on Online Big Data

Abstract

With the rapid development of the Internet, the Internet has become a new platform for gathering public opinion. Therefore, studying the sentiment of public opinion regarding education on the Internet is of great value in understanding the current situation of education. In this study, a web crawler is used to collect data related to education public opinion online, and an attention mechanism is used to extract data related to the sentiment of education public opinion. Subsequently, the convolutional neural network is used to extract sentiment features, and the sentiment features are classified and processed by the softmax classifier. Finally, the sentiment visualisation system for educational public opinion is designed by combining the sentiment analysis method. It is verified that the accuracy and F1 value of the sentiment analysis model proposed in this paper are the highest compared to the comparative models. The period of 2021-2022 is the high incidence period of online education public opinion events, and there are two obvious peaks of sentiment intensity in the typical cases of education public opinion A and B, which are the early stage of the outbreak of the online public opinion and the period of the official investigation and update, respectively. In this paper, we use visualization to show changes in people’s emotions related to education public opinion, hoping that it can provide a reference for managing education public opinion by relevant departments.