A fog‐computing architecture for network public opinion monitoring based on intelligent semantic recognition

Currently, the online data contains rich user emotional information and public opinion information. These data can provide massive support for network public opinion monitoring and analysis. However, there are two problems in the network public opinion analysis of the online data. On the one hand, a vast amount of online data with discursiveness and concealment are processed in the cloud platforms, which consumes a long time. On the other hand, the massive online public opinion data is disperse and hidden, resulting in the dependence on manual screening for the analysis of public opinion. Therefore, it is still an important challenge to study the efficient and low‐latency extraction of valuable information from network public opinion. In this paper, we proposed a fog computing based framework using the technologies of intelligent semantic recognition and data mining for the analysis of network public opinion. Firstly, we build a fog computing architecture to collect the text data of network public opinion. Then, an efficient network public opinion model is constructed by intelligence semantic recognition. Finally, we achieve the function of public opinion analysis and early warning. The experimental results show that the method proposed in this paper achieves better performance against some existing methods.