Title: Research on government network public opinion monitoring algorithm under the background of sustainable smart government

Authors: Shiwei Zhang

Addresses: School of Public Policy and Management, China University of Mining and Technology, Xuzhou, 221116, China; School of Social Development and Public Administration, Suzhou University of Science and Technology, Suzhou, 215009, China

Abstract: It is very necessary for the government to strengthen the supervision of network information. Considering the problems of over fitting and gradient disappearance in the traditional bi directional long short-term memory (BiLSTM) network, the regularisation method is used to adjust the input weight of the model. At the same time, 333 functions is used to replace tanh activation function to build a government network public opinion monitoring model of double-layer long short-term memory network (RLSTM). The model performance test results show that in dataset type 1, the public opinion prediction accuracy is 0.993, and in dataset type 2, the public opinion prediction accuracy is 0.982, and the prediction performance is the best. At the same time, the improved RLSTM model also has excellent performance in the test of model convergence effect and error performance. The research content is of great significance to strengthen the security supervision of network information.

Keywords: smart government; RLSTM model; public opinion; monitoring.

DOI: 10.1504/IJNVO.2023.133844

International Journal of Networking and Virtual Organisations, 2023 Vol.28 No.2/3/4, pp.231 - 246

Received: 14 Sep 2022
Accepted: 14 Jan 2023
Published online: 04 Oct 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article