Network Structure and Community Evolution Online: Behavioral and Emotional Changes in Response to COVID-19

Revealing Public Opinion towards the COVID-19 Vaccine with Weibo Data in China: BertFDA-Based Model

The COVID-19 pandemic has created unprecedented burdens on people's health and subjective well-being. While countries around the world have established models to track and predict the affective states of COVID-19, identifying the topics of public discussion and sentiment evolution of the vaccine, particularly the differences in topics of concern between vaccine-support and vaccine-hesitant groups, remains scarce. Using social media data from the two years following the outbreak of COVID-19 (23 January 2020 to 23 January 2022), coupled with state-of-the-art natural language processing (NLP) techniques, we developed a public opinion analysis framework (BertFDA). First, using dynamic topic clustering on Weibo through the latent Dirichlet allocation (LDA) model, a total of 118 topics were generated in 24 months using 2,211,806 microblog posts. Second, by building an improved Bert pre-training model for sentiment classification, we provide evidence that public negative sentiment continued to decline in the early stages of COVID-19 vaccination. Third, by modeling and analyzing the microblog posts from the vaccine-support group and the vaccine-hesitant group, we discover that the vaccine-support group was more concerned about vaccine effectiveness and the reporting of news, reflecting greater group cohesion, whereas the vaccine-hesitant group was particularly concerned about the spread of coronavirus variants and vaccine side effects. Finally, we deployed different machine learning models to predict public opinion. Moreover, functional data analysis (FDA) is developed to build the functional sentiment curve, which can effectively capture the dynamic changes with the explicit function. This study can aid governments in developing effective interventions and education campaigns to boost vaccination rates.

Emoji use in China: popularity patterns and changes due to COVID-19

Emojis are small pictograms that are frequently embedded within micro-texts to more directly express emotional meanings. To understand the changes in the emoji usage of internet users during the COVID-19 outbreak, we analysed a large dataset collected from Weibo, the most popular Twitter-like social media platform in China, from December 1, 2019, to March 20, 2020. The data contained 38,183,194 microblog posts published by 2,239,472 unique users in Wuhan. We calculated the basic statistics of users’ usage of emojis, topics, and sentiments and analysed the temporal patterns of emoji occurrence. After examining the emoji co-occurrence structure, we finally explored other factors that may affect individual emoji usage. We found that the COVID-19 outbreak greatly changed the pattern of emoji usage; i.e., both the proportion of posts containing emojis and the ratio of users using emojis declined substantially, while the number of posts remained the same. The daily proportion of Happy emojis significantly declined to approximately 32%, but the proportions of Sad- and Encouraging-related emojis rose to 24% and 34%, respectively. Despite a significant decrease in the number of nodes and edges in the emoji co-occurrence network, the average degree of the network increased from 34 to 39.8, indicating that the diversity of emoji usage increased. Most interestingly, we found that male users were more inclined towards using regular textual language with fewer emojis after the pandemic, suggesting that during public crises, male groups appeared to control their emotional display. In summary, the COVID-19 pandemic remarkably impacted individual sentiments, and the normal pattern of emoji usage tends to change significantly following a public emergency.