Situation Analysis and Prediction of Web Public Sentiment

Public sentiment reflects the people´s attitude to society and politics. Since Web public sentiment sees most similarity with social network, in this paper we use threelayers social network to analyze Web public sentiment, and we use relative centrality and potential center to find the key node and we propose a new solution for analyzing and predicting the public sentiment situation by applying the chaos theory, that is, through one-dimensional time series to reversely construct the phase space structure of the original system and find the hidden evolution law of chaotic attractor. The prediction wins precious time for relevant department to formulate corresponding policies to deal with the situation and for mainstream media to steer the correct public opinion.