Editorial
Risk Early Warning for Police-Related Online Public Opinion Based on Deep Learning
@ARTICLE{10.4108/eetsis.10664, author={Juan Wang and Yuxiang Guan and Nan Wang and Jie Pan and Peng Zhang}, title={Risk Early Warning for Police-Related Online Public Opinion Based on Deep Learning}, journal={EAI Endorsed Transactions on Scalable Information Systems}, volume={12}, number={6}, publisher={EAI}, journal_a={SIS}, year={2025}, month={12}, keywords={Police-related online public opinion, Deep learning, Risk early warning, Optimization algorithm}, doi={10.4108/eetsis.10664} }- Juan Wang
Yuxiang Guan
Nan Wang
Jie Pan
Peng Zhang
Year: 2025
Risk Early Warning for Police-Related Online Public Opinion Based on Deep Learning
SIS
EAI
DOI: 10.4108/eetsis.10664
Abstract
INTRODUCTION: Police-related online public opinion is highly sensitive and can easily have a negative impact on social stability. OBJECTIVES: This paper aims to address the crucial need for early warning systems for the risks associated with police-related online public opinion to ensure social harmony and effectively prevent and resolve major social risks. METHODS: Based on a literature review and deep learning methods, this research constructs an indicator system from four dimensions, analyzing data from representative police-related online public opinion incidents over the past five years. A CNN-BiLSTM sentiment classification model is built for sentiment analysis, and an optimized SSA-CNN-LSTM-Attention model is used for public opinion risk early warning. RESULTS: The experimental results demonstrate that the SSA-CNN-LSTM-Attention model has the minimum error. CONCLUSION: This research provides a theoretical reference for public security organs in responding to and preventing police-related online public opinion.
Copyright © 2025 Juan Wang et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
