Abstract
Online public opinion reflects social conditions and public attitudes regarding special social events. Therefore, analyzing the temporal and spatial distributions of online public opinion topics can contribute to understanding issues of public concern, grasping and guiding the developing trend of public opinion. However, how to evaluate the validity of classification of online public opinion remains a challenging task in the topic mining field. By combining a Bidirectional Encoder Representations from Transformers (BERT) pre-training model with the Latent Dirichlet Allocation (LDA) topic model, we propose an evaluation method to determine the optimal classification number of topics from the perspective of semantic similarity. The effectiveness of the proposed method was verified based on the standard Chinese corpus THUCNews. Taking Coronavirus Disease 2019 (COVID-19)-related geotagged posts on Weibo in Wuhan city as an example, we used the proposed method to generate five categories of public opinion topics. Combining spatial and temporal information with the classification results, we analyze the spatial and temporal distribution patterns of the five optimal public opinion topics, which are found to be consistent with the epidemic development, demonstrating the feasibility of our method when applied to practical cases.
Highlights
In the era of big data, the number of netizens has been increasing annually [1]
The analysis of online public opinion under the epidemic situation is of great significance for guiding public opinion and gaining access to public sentiment and public events
Utilizing a Bidirectional Encoder Representations from Transformers (BERT) pre-training model for word embedding, we proposed a semantic similarity-related evaluation method to finding the optimal number of topics generated by the Latent Dirichlet Allocation (LDA) model, adopted this method to analyze the online public opinion of check-in microblogs
Summary
Social media provides important platforms for Internet users to express and exchange their views, as well as to obtain information. Once a significant event occurs, the public tends to describe their attention to and cognition of the event on social media platforms, leading to dissemination and discussion of the topic. 2020, the discovery of COVID-19 and lockdown policy prompted the public to exchange information on social media platforms in order to learn about the epidemic [2]. Twitter, has become an important source for obtaining social sentiment and analyzing public opinion. Topic classification has a pivotal role in public opinion analysis, on which a considerable amount of literature [2,3,4,5,6] has been published regarding
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
