Modeling of Student Group Public Opinion Dissemination Mechanism Based on Graph Convolutional Networks in Ideological and Political Education in Colleges and Universities

Predicting the trend of public opinion dissemination of student groups is of great significance for improving the level of ideological and political education in colleges and universities, and this paper studies the modeling of the mechanism of public opinion dissemination of student groups. Firstly, the relevant theoretical foundation of social network is introduced, and the public opinion propagation model SIR model is proposed. Then, it proposes an opinion propagation prediction method based on representation learning and graph convolutional network, and designs CNN-GCN for predicting the behavior of student groups, and obtains the development trend of opinion topics by time slicing the active period of opinion topics. Applying the model of this paper to the public opinion of student groups in ideological and political education in colleges and universities, we know from the effect comparison that the monitoring effect of this paper’s model is more ideal than the experimental comparison model. Its ACC values on Twitter15 and Twitter16 are 0.993 and 0.998 respectively, which are higher than other benchmark models. This proves the superiority of the model proposed in this paper.