Internet public opinion chaotic prediction based on Support Vector Regression machine

In order to improve the prediction accuracy of internet public opinion, this paper proposes an internet public opinion prediction model based on chaotic theory and Support Vector Regression. The internet public opinion time series proves to be with chaos characteristics, and then delay time and embedding dimension are calculated using mutual information method and G-P method respectively according to takens theorem, and the internet public opinion time series is reconstructed in phase space. The internet public opinion forecasting model is established using Support Vector Regression, and the simulation experiment is carried out with comparison models. The experimental results show that, compared with other models, the proposed model has improved the prediction accuracy and stability of internet public opinion and the prediction results have practical value.