Prediction algorithm for public health and emergency monitoring based on a social network

The progress and development of social networks have significantly enriched data information. The analysis of disease information extracted from social networks makes the development of public health convenient. In this study, the general and emergent features of influenza were used as examples, and the Chinese microblogging website Sina Weibo was used as the main data source. Moreover, auxiliary analysis with reference data for PM2.5 was conducted. The source data were processed via keyword filtering, and results of the k-nearest neighbors and support vector machine algorithms were compared. The results of the optimal algorithm were adopted as the core data, which were then compared with the data from the Centers for Disease Control and Prevention to verify the validity of the former. In addition, the correlation was verified with reference PM2.5 data. Finally, a dynamic Bayesian algorithm and a hidden Markov model were used to validate the accuracy of the prediction algorithm. In practical applications, the proposed algorithm can effectively control the potential of a large-scale epidemic, thereby making it helpful in monitoring public health.