Abstract
The purpose of this article is to analyse the emotional evolution of the netizens in reaction to the events of the Anti-ELAB (Anti-Extradition Law Amendment Bill) movement in Hong Kong. We attempt to investigate evolving laws of large-scale Internet public opinion events and provide relevant agencies with a theoretical basis for a public opinion response mechanism. On the basis of improving the Bidirectional Encoder Representations from Transformers (BERT) pre-training task, we add in-depth pre-training tasks, and based on the optimisation results of the LDA topic embedding, we integrate deeply with the LDA model to dynamically present the fine-grained public sentiment of the event. Through the collection of large-scale text data related to the Anti-ELAB Movement from a well-known forum in Hong Kong, a BERT-LDA hybrid model for large-scale network public opinion analysis is constructed in a complex context. Through empirical analysis, we calculate and reveal the emotional change process of netizens and opinion leaders in the three transition stages of the Anti-ELAB Movement with the evolution of the topic word as the core by visualisation. We also analyse the emotional distribution and evolution trend of public opinion under the `text topic', and deeply analyse the character and role of opinion leaders in Anti-ELAB public opinion events. The improved BERT-LDA model or sentiment classification AUC value exceeds 99.6% in the sentiment classification task for the Anti-ELAB Movement.
Highlights
In June 2020, on the first anniversary of the birth of the Anti-ELAB Movement, the National Security Law was officially promulgated and implemented in Hong Kong
We focussed on the hot Internet public opinion incident of the Anti-ELAB Movement
An improved Bidirectional Encoder Representations from Transformers (BERT)-LDA hybrid model was constructed in a complex Cantonese context, involving the mixture of Chinese and English, as well as traditional characters and emoticons
Summary
In June 2020, on the first anniversary of the birth of the Anti-ELAB Movement, the National Security Law was officially promulgated and implemented in Hong Kong. The second is how to deeply integrate the advantages of the BERT and LDA models so that the improved BERT-LDA model cannot only make up for the deficiencies of the LDA bagof-words model, and provide topic-dimensional semantic information for sentiment analysis tasks of large-scale complex text In this way, we can fully grasp the netizen’s emotional evolutionary context of the Hong Kong Anti-ELAB Movement, explore the evolutionary laws of such large-scale public opinion incidents, and provide a theoretical basis for government departments to formulate effective measures. The main contributions of our proposed work are highlighted below: a) we effectively integrate the LDA topic model and the BERT word embedding model to optimize the topic vector to realize topic clustering; b) We improved the BERT pre-training task and superimposed the deep pretraining task; c) We propose a large-scale network public opinion event sentiment evolution analysis model. The remainder of the paper is organized as follows: Section II introduces the LDA topic optimization model and the BERT deep learning improvement model, and describes our proposed model and algorithm in detail; empirical analysis of the Internet public opinion and sentiment in Hong Kong Anti-ELAB movement are presented in Section III; Section IV concludes this paper
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
