Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Welcome to the InfoSci Platform
Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment

Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment

Hanqing Sun, Zheng Liu, Weimin Lian, Guizhi Wang
Copyright: © 2024 |Volume: 17 |Issue: 1 |Pages: 18
ISSN: 1935-570X|EISSN: 1935-5718|EISBN13: 9798369323182|DOI: 10.4018/IJITSA.352509
Cite Article Cite Article

MLA

Sun, Hanqing, et al. "Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment." IJITSA vol.17, no.1 2024: pp.1-18. http://doi.org/10.4018/IJITSA.352509

APA

Sun, H., Liu, Z., Lian, W., & Wang, G. (2024). Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment. International Journal of Information Technologies and Systems Approach (IJITSA), 17(1), 1-18. http://doi.org/10.4018/IJITSA.352509

Chicago

Sun, Hanqing, et al. "Social Network Public Opinion Analysis Using BERT-BMA in Big Data Environment," International Journal of Information Technologies and Systems Approach (IJITSA) 17, no.1: 1-18. http://doi.org/10.4018/IJITSA.352509

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The existing social network public opinion analysis methods have problems such as poor semantic expression quality and weak detection ability in short texts. Therefore, a social network public opinion analysis method based on BERT-BMA is proposed. To normalize the comment text, the rumor text is initially transferred to a word vector matrix using the BERT (Bidirectional Encoder Representations from Transformer) model. The BiLSTM-based network architecture is subsequently employed to acquire the trace features of data transmission. Ultimately, this study employs the multi-head attention mechanism to extract feature information that is more significant in the analysis of online public opinion by mining the dependency relationships between users, resulting in increasing ability to detect public opinion emergencies. The experimental outcomes indicate that the results on the Twitter data set and Weibo dataset are superior to other comparative models.