Dual Consistency-enhanced Semi-supervised Sentiment Analysis towards COVID-19 Tweets

In the context of COVID-19, numerous people present their opinions through social networks. It is thus highly desired to conduct sentiment analysis towards COVID-19 tweets to learn the public's attitudes, and facilitate the government to make proper guidelines for avoiding the social unrest. Although many efforts have studied the text-based sentiment classification from various domains (e.g., delivery and shopping reviews), it is hard to directly use these classifiers for the sentiment analysis towards COVID-19 tweets due to the domain gap. In fact, developing the sentiment classifier for COVID-19 tweets is mainly challenged by the limited annotated training dataset, as well as the diverse and informal expressions of user-generated posts. To address these challenges, we construct a large-scale COVID-19 dataset from Weibo and propose a dual COnsistency-enhanced semi-superVIseD network for Sentiment Anlaysis (COVID-SA). In particular, we first introduce a knowledge-based augmentation method to augment data and enhance the model's robustness. We then employ BERT as the text encoder backbone for both labeled data, unlabeled data, and augmented data. Moreover, we propose a dual consistency (i.e., label-oriented consistency and instance-oriented consistency) regularization to promote the model performance. Extensive experiments on our self-constructed dataset and three public datasets show the superiority of COVID-SA over state-of-the-art baselines on various applications. IEEE

The Wuhan Lockdown

The book's middle chapters examine the various bold and careful acts of Wuhan residents during the lockdown. A scrupulous student of China's internet, Yang devotes most of his attention to analyzing China's fast-changing internet culture through the lens of the Wuhan lockdown. After the Wuhan lockdown in early 2020, China imposed lockdown in every city where there was an outbreak, until it lifted the zero COVID policy in December 2022. [Extracted from the article] Copyright of Journal of Asian Studies is the property of Duke University Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Text Mining and Emotion Classification on Monkeypox Twitter Dataset: A Deep Learning-Natural Language Processing (NLP) Approach

Emotion classification has become a valuable tool in analyzing text and emotions people express in response to events or crises, particularly on social media and other online platforms. The recent news about monkeypox highlighted various emotions individuals felt during the outbreak. People’s opinions and concerns have been very different based on their awareness and understanding of the disease. Although there have been studies on monkeypox, emotion classification related to this virus has not been considered. As a result, this study aims to analyze the emotions individual expressed on social media posts related to the monkeypox disease. Our goal is to provide real-time information and identify critical concerns about the disease. To conduct our analysis, first, we extract and preprocess 800,000 datasets and then use NRCLexicon, a Python library, to predict and measure the emotional significance of each text. Secondly, we develop deep learning models based on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and the combination of Convolutional Neural Networks and Long Short-Term Memory (CLSTM) for emotion classification. We use SMOTE (Synthetic Minority Oversampling Technique) and Random Undersampling techniques to address the class imbalance in our training dataset. The results of our study revealed that the CNN model achieved the highest performance with an accuracy of 96%. Overall, emotion classification on the monkeypox dataset can be a powerful tool for improving our understanding of the disease. The findings of this study will help develop effective interventions and improve public health. Author

Social Media Transforming Tourist Behavior: Leading Towards Overtourism

Most admired and exotic tourist destinations around the globe are distress from challenges posed by overtourism, which in turn affect the well-being of nature and humans. The causes of overtourism are many but social media can be considered as the foremost reason for overtourism in the era of web 2.0. This chapter aims to address the role of social media in transforming the behavior of tourist by descriptive research approach using secondary sources of information collected from e-resources, journals, articles, and books. It has been concluded from the literature analysis that social media plays a tremendous part in transforming the behavior of tourist due to the craze of user-generated content like reviews, selfies, photographs, visuals, and lots more. A positive attempt has been made to suggest ways to combat overtourism. Tourist behavior has been changed due to the novel coronavirus. Impact of COVID-19 on overtourism has also been touched to provide insight. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

Don't Be a Victim during a Pandemic! Analysing Security and Privacy Threats in Twitter during COVID-19

There has been a huge spike in the usage of social media platforms during the COVID-19 lockdowns. These lockdown periods have resulted in a set of new cybercrimes, thereby allowing attackers to victimise social media users with a range of threats. This paper performs a large-scale study to investigate the impact of a pandemic and the lockdown periods on the security and privacy of social media users. We analyse 10.6 Million COVID-related tweets from 533 days of data crawling and investigate users' security and privacy behaviour in three different periods (i.e., before, during, and after the lockdown). Our study shows that users unintentionally share more personal identifiable information when writing about the pandemic situation (e.g., sharing nearby coronavirus testing locations) in their tweets. The privacy risk reaches 100% if a user posts three or more sensitive tweets about the pandemic. We investigate the number of suspicious domains shared on social media during different phases of the pandemic. Our analysis reveals an increase in the number of suspicious domains during the lockdown compared to other lockdown phases. We observe that IT, Search Engines, and Businesses are the top three categories that contain suspicious domains. Our analysis reveals that adversaries' strategies to instigate malicious activities change with the country's pandemic situation. © 2013 IEEE.

Using Machine Learning to Establish the Concerns of Persons with HIV/AIDS During the COVID-19 Pandemic from their Tweets

There are millions of People Living with HIV/AIDS (PLWHA) globally and over the years, addressing their concerns has been topical for many stakeholders. It is a well-known and established fact that PLWHA are at increased risk of victimization and stigmatization. Unfortunately, the world experienced an outbreak of the COVID-19 pandemic that has led to strict social measures in many states. Thus, it is the goal of this research to study the impact that the outbreak and its mitigation measures have had on the PLWHA. Specifically, we sought to highlight their concerns from sentiments expressed on social media based on posted tweets. By combining machine learning (ML) techniques such as textual mining and thematic analysis, we determined 14 major themes as factors that are worth exploring. In this work, we originally extracted 2,839,091 tweets related to HIV/AIDS posted from March 2020 to April 2022. After initially doing data cleaning and preprocessing, we performed topic modeling using the Latent Dirichlet Allocation (LDA) topic model to extract 25 topics that are made up of 30 keywords each. The topics were then narrowed into 14 themes. The paper details the negative, positive, and neutral sentiment polarities which we highlight as concerning. These sentiments were determined using the Valence Aware Dictionary and sEntiment Reasoner (VADER) Sentiment Analysis Library with a 90% F1-score compared to TextBlob which showed a 53% F1-score. The research findings highlight issues affecting PLWHA during and post-pandemic such as high cost of medical care, late diagnosis of HIV, limited access to medications, stigmatization and victimization, absence of testing kits in hospitals, and lack of urgency in the development of vaccines or cure for HIV. Author

1000 days of COVID-19: A gender-based long-term investigation into attitudes with regards to vaccination

The coronavirus pandemic has undoubtedly been one of the major recent events that have affected our society at the global level. During this period, unprecedented measures have been imposed worldwide by authorities in an effort to contain the spread of the disease. These measures have led to a worldwide debate among the public, occurring not least within the forum of social media, tapping into pre-existing trends of skepticism, such as vaccine hesitancy. At the same time, it has become apparent that the pandemic affected women and men differently. With these two themes in view, the paper aims to analyze using a data-driven approach the evolution of opinions with regards to vaccination against COVID-19 throughout the entire duration of the pandemic from the point of view of gender. For this analysis, approximately 1,500,000 short user-contributed texts have been retrieved from the popular microblogging platform Twitter, posted between 30 January 2020 and 30 November 2022. Using a machine learning approach, several classifiers have been trained to identify the likely gender (female or male) of the author, as well as the stance of the specific post towards the COVID-19 vaccines (neutral, in favor, or against), achieving 85.69% and 93.64% weighted accuracy measures for each problem, respectively. Based on this analysis, it can be observed that most tweets exhibit a neutral stance, while the number of tweets in favor of vaccination is greater than the number of tweets opposing vaccination, with the distribution varying across time in response to specific events. The subject matter of the tweets varied more between stances than between genders, suggesting that there is no significant difference between the contents of tweets posted by females and males. We also find that while the overall engagement on Twitter with the topic of vaccination against COVID-19 is on the wane, there has been a rise in the number of against tweets continuing into the present. Author

The Wuhan Lockdown

Chapter seven similarly shows how, despite censorship and propaganda, netizens' counter-censorship activities sometimes prevailed. ISBN 9780231200479 Guobin Yang's book is a vivid and highly readable account of the first months of what became the COVID-19 pandemic in Wuhan as revealed through the online diaries of Wuhan residents. In chapters eight and nine, Yang deals with the important topics of COVID nationalism, and "mourning and remembering.". [Extracted from the article] Copyright of China Quarterly is the property of Cambridge University Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

An exploration into the educational benefits and challenges of a student-led blog for part-time higher education students

This study investigates the perspectives of part-time students and academics on the uses of blogs within Higher Education. It examines blogging within a socio-cultural framework through the theoretical lens of connectivism (Siemens, 2009, 2018;Downes, 2012). Qualitative methodologies are utilised in the interpretivist paradigm to understand the challenges and benefits of using a blog. This research reports Academic and student views regarding the usefulness of blogging for educational purposes, describes how and why blogs are used and reveals why uptake for some students is limited.A small-scale research project, using thematic analysis to investigate samples of student blogs and examine interview data, involved the analysis of the contents of 12 students' blogs, followed by interviews with students (n=8) and academics (n=4). This research took place at two universities in the East Midlands, and focussed on two professional education courses during the first term of the first year of study. The findings identified benefits for students, both in their academic and reflective writing and in synthesising theory with their professional practice. However, the need for appropriate training to combine pedagogical design with collaborative technologies, accessible to both staff and students, emerges as an essential priority. Moreover, it was important to understand the broader context of multiple online platforms and face-to-face communication that students are already accessing. Finally, traditional delivery models within practices and concepts of academic and student roles, i.e., expert and novice, limit the role of the 'More Knowledgeable Other' (MKO) to the academic alone, which influences how the blog was viewed, used and valued within student groups.The findings further developed Garcia et al. (2013) model of connectivism and supports that learning occurs within a fluid and dynamic context online. In this evolved model, the various students can be centrally vii active or more passive at different times but still engaged. All the actors have agency in this sense, even when they choose to behave as 'lurkers'. The findings suggest that this new model recognises the vital importance of the expert within the system and argues that, for blogs to achieve maximum benefit, the academic needs to play a central role (at least initially).Recommendations are contextualised as part of a set of potential responses to the current COVID-19 pandemic and post-pandemic climate, as blogging could play an important role in a range of online teaching scenarios in higher education (HE). (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Machine Learning Techniques for Sentiment Analysis of COVID-19-Related Twitter Data

On Twitter, COVID-19 is a highly discussed topic. People worldwide have used Twitter to express their viewpoints and feelings during the pandemic. Previous research has focused on particular topics such as the public's sentiment during the lockdown, their opinion on governmental measures, or their stance towards COVID-19 vaccines. However, until today, there is no comprehensive overview that presents possible areas of application for sentiment analysis of COVID-19 Twitter data. Therefore, this study reveals how sentiment analysis can provide relevant insights for managing the pandemic by applying a behavioral and social science lens. In this context, our systematic literature review focuses on machine learning-based sentiment analysis techniques and compares the best-performing classification algorithms for COVID-19-related Twitter data. We performed a search in five databases, which are: IEEE Xplore DL, ScienceDirect, SpringerLink, ACM DL, and AIS Electronic Library. This search resulted in 40 papers published between October 2019 and January 2022 that used sentiment analysis to evaluate the public opinion on COVID-19-related topics, which we further investigated. Our research indicates that the best performing models in terms of accuracy are ensemble models that comprise various machine learning classifiers. Especially BERT and RoBERTa models provide the most promising results when fine-tuned on Twitter data. Our study aims to combine machine learning-based sentiment analysis and insights from social and behavioral science to provide decision-makers and public health experts with guidance on the application of sentiment analysis in the fight against the spread of COVID-19. © 2013 IEEE.

Pro or Anti? A Social Influence Model of Online Stance Flipping

Social influence characterizes the change of an individual's stances in a complex social environment towards a topic. Two factors often govern the influence of stances in an online social network: endogenous influences driven by an individual's innate beliefs through the agent's past stances and exogenous influences formed by social network influence between users. Both endogenous and exogenous influences offer important cues to user susceptibility, thereby enhancing the predictive performance on stance changes or flipping. In this work, we propose a stance flipping prediction problem to identify Twitter agents that are susceptible to stance flipping towards the coronavirus vaccine (i.e., from pro-vaccine to anti-vaccine). Specifically, we design a social influence model where each agent has some fixed innate stance and a conviction of the stance that reflects the resistance to change;agents influence each other through the social network structure. From data collected between April 2020 to May 2021, our model achieves 86% accuracy in predicting agents that flip stances. Further analysis identifies that agents that flip stances have significantly more neighbors engaging in collective expression of the opposite stance, and 53.7% of the agents that flip stances are bots and bot agents require lesser social influence to flip stances. © 2013 IEEE.

Vaccine Hesitancy Hotspots in Africa: An Insight From Geotagged Twitter Posts

Many social media users express concerns about vaccines and their side effects on Twitter. These concerns lead to a compromise of confidence which brings about vaccine hesitancy. In Africa, vaccine hesitancy is a major challenge faced by health policymakers in the fight against COVID-19. Given that most tweets are geotagged, clustering them according to their sentiments could help identify locations that may likely experience vaccine hesitancy for health policy and planning. In this study, we collected 70 000 geotagged vaccine-related tweets in nine African countries, from December 2020 to February 2022. The tweets were classified into three sentiment classes—positive, negative, and neutral. The quality of the classification outputs was achieved using Naíve Bayes (NB), logistic regression (LR), support vector machines (SVMs), decision tree (DT), and K-nearest neighbor (KNN) machine learning classifiers. The LR achieved the highest accuracy of 71% with an average area under the curve of 85%. The point-based location technique was used to calculate the hotspots based on the locations of the classified tweets. Locations with green, red, and gray backgrounds on the map signify a hotspot for positive, negative, and neutral sentiments. The outcome of this research shows that discussions on social media can be analyzed to identify hotspots during a disease outbreak, which could inform health policy in planning and management of vaccine hesitancy in Africa. Author

Exploring the Types of Blogs Cited in Urban Planning Research

This article discusses the crucial role of blogs in reporting topical materials yet to be adequately discussed in scholarly journals. A scoping study examined 31 samples from 4 types of blogging sources cited in 10 publications published in 7 journals in 2020. We identified four categories of blogs that include 39 community organisations, academics, practitioners, and community members who are readers of these blogs. We discuss the areas in which these blogs have affected public discourse over COVID-19. We also show that the blogs are based on novel concepts that have not yet been subject to the peer review process.

Inonder l'espace médiatique, contester le manque de transparence de l'État: L'importance de la criminologie de l'actualité en temps de pandémie

Il y a eu des différences importantes concernant la divulgation proactive des cas de coronavirus, parmi les prisonniers et le personnel pénitentiaire, entre les juridictions canadiennes au cours des deux premières années de la pandémie COVID-19. S'appuyant sur la littérature sur la police des connaissances criminologiques et l'opacité des prisons, cet article aborde comment de multiples approches de la criminologie de l'actualité (« newsmaking criminology »), sous la forme d'articles de blogues, de rédaction d'éditoriaux, de publication de rapports et de commentaires d'experts, peuvent aider à remettre en question le manque de transparence de l'État afin de générer une divulgation proactive d'informations supplémentaires sur l'impact et la gestion du coronavirus derrière les murs de la prison. Nous explorons comment l'approche « inonder l'espace » des débats publics sur la gestion de la pandémie avec les informations limitées et incomplètes mises à disposition par les autorités fonctionne comme une stratégie de mobilisation des connaissances et de recherche pour faciliter la diffusion d'informations précédemment non publiées qui sont essentielles pour éclairer les politiques, les pratiques et les résultats de l'enfermement. Ce faisant, nous soulignons la valeur de la criminologie de l'actualité non seulement comme moyen de communiquer et de mobiliser les connaissances criminologiques, mais aussi de les générer au service de la recherche émancipatrice et militante.Alternate :Over the course of the COVID-19 pandemic, Canadian jurisdictions have varied in terms of their reporting of COVID-19 cases amongst prisoners and prison staff. By engaging with the literature focused on the policing of criminological knowledge and prison opacity, this paper examines how multiple approaches to newsmaking criminology in the form of blog posts, op-ed writing, the publishing of reports, and expert commentary can challenge state secrecy in ways that help generate proactive disclosure of additional information regarding the impact and management of the coronavirus behind prison walls. We explore how "flooding the zone" of public debates on pandemic management with the limited and incomplete data made available by authorities works as a knowledge mobilization and research strategy to help reveal previously unpublished information critical to better understanding prison policy, practice and outcomes. In so doing, we highlight the value of newsmaking criminology not only as a means of communicating and mobilizing criminological knowledge, but also of generating it in the service of emancipatory research and advocacy.Alternate :Durante los dos primeros años de la pandemia de COVID-19, hubo diferencias significativas en la divulgación proactiva de los casos de coronavirus, entre los reclusos y el personal penitenciario, entre las jurisdicciones canadienses. Basándose en los estudios sobre la vigilancia del conocimiento criminológico y la opacidad de las prisiones, este artículo analiza cómo los múltiples enfoques de la criminología mediática (« newsmaking criminology »), en forma de entradas de blog, redacción de editoriales, publicación de informes y comentarios de expertos, pueden ayudar a cuestionar la falta de transparencia del Estado para generar una divulgación proactiva de información adicional sobre el impacto y la gestión del coronavirus tras los muros de las prisiones. Exploramos cómo el enfoque de « inundar el espacio » de los debates públicos sobre la gestión de la pandemia con la información limitada e incompleta puesta a disposición por las autoridades funciona como una estrategia de movilización del conocimiento y de investigación para facilitar la difusión de información inédita que es fundamental para informar la política, la práctica y los resultados del confinamiento. De este modo, destacamos el valor de la criminología mediática no sólo como medio de comunicación y movilización del conocimiento criminológico, sino también para genera lo al servicio de la investigación emancipadora y activista.

Public health interventions: the elephant in the room of the health system crisis

Since 2020, the "rules of engagement" for our health system, the expected and relatively predictable level of ill-health in the community, have changed.1 COVID-19 has increased demand for healthcare through multiple pathways. [...]through managing those acutely unwell with COVID-19 infection, which during 2022 has been a significant source of hospitalisation over the three waves. [...]by creating a large burden of "catch up" care needed for those people whose care was delayed due to beds being occupied by those infected with COVID-19. While there is common perception that pub- lic health actions take decades to have impacts, the authors of these blogs identified a wide range of interventions that would have such as vaccination, raising alcohol taxes, lowering drink driving levels, a health-based approach to drug harms, speed limit reductions, increasing benefit levels, alterations to streets to promote cycling and walking and reformulation of processed foods.12-17 These interventions would impact on a wide range of health conditions, both physical and mental.

Pro or Anti? A Social Influence Model of Online Stance Flipping

Social influence characterizes the change of an individual's stances in a complex social environment towards a topic. Two factors often govern the influence of stances in an online social network: endogenous influences driven by an individual's innate beliefs through the agent's past stances and exogenous influences formed by social network influence between users. Both endogenous and exogenous influences offer important cues to user susceptibility, thereby enhancing the predictive performance on stance changes or flipping. In this work, we propose a stance flipping prediction problem to identify Twitter agents that are susceptible to stance flipping towards the coronavirus vaccine (i.e., from pro-vaccine to anti-vaccine). Specifically, we design a social influence model where each agent has some fixed innate stance and a conviction of the stance that reflects the resistance to change;agents influence each other through the social network structure. From data collected between April 2020 to May 2021, our model achieves 86% accuracy in predicting agents that flip stances. Further analysis identifies that agents that flip stances have significantly more neighbors engaging in collective expression of the opposite stance, and 53.7% of the agents that flip stances are bots and bot agents require lesser social influence to flip stances.

The COVID-19 Vaccine Opinions of Women Planning a Pregnancy: International Web Blogs Scanning.

Background: The unprecedented COVID-19 has infected millions of people and killed hundreds of thousands of people. A strategy to contain the spread of the disease was the development of the COVID-19 vaccine. Objective: In our study, it was determined the opinions of women who are planning to become pregnant about the COVID-19 vaccine. Methods: Blogs were used as the data source in the research, which was designed as a descriptive qualitative study. For this purpose, the expressions of 34 women identified between February and March 2021 were evaluated with directed qualitative content analysis. Results: Psychological changes, cognitive changes, and coping methods were determined as the themes of our results. This study demonstrates the value of using qualitative methods to determine the thoughts of women planning to become pregnant regarding the COVID-19 vaccine. Conclusion: For women planning pregnancy, continued research into vaccine safety and efficacy is vital, and results should be carefully investigated and handed in the right channels.

APRESENTAÇÃO

No final de março de 2020, quando os efeitos da covid-19 já eram evidentes em todo o mundo e começavam a se intensificar no Brasil, incluindo a interrupçao das aulas e demais atividades académicas presenciais nas universidades, o blog da Biblioteca Virtual do Pensamento Social (BVPS)1 iniciou, em parceria com a revista Sociologia & Antropologia, uma coluna aberta sobre o tema, intitulada "Pandemia, Cultura e Sociedade". Depois de cerca de um mes publicando a coluna, o blog deu inicio, em parceria com S&A e a Sociedade Brasileira de Sociologia (SBS), ao simpósio "Mundo Social e Pandemia". Por fim, incluimos ao final do número o simpósio "Mundo Social e Pandemia", organizado por Andre Bittencourt (UFRJ/blog BVPS) e Mauricio Hoelz (UFRRJ/SBS), que reúne as respostas de 70 cientistas sociais pertencentes a instituiçoes de pesquisa de 18 países e cinco continentes.

Utilizing Blogs on ESL learners' vocabulary learning through social constructivist theory: A descriptive study.

During this period in history, the advancement of technology is developing at a fast pace, and it is becoming more important to every normal person. In particular, the smart phone, which is quickly becoming one of the most frequently used gadgets in ordinary life, is no longer considered a luxury commodity. Because of the COVID-19 epidemic, students are not required to utilise textbooks while studying. Beyond textbooks, there are numerous other media that may be used to advance an individual's education and development. The purpose of this research study is to investigate the effect of social media, namely Blogs, on the vocabulary acquisition of ESL students. A questionnaire was adopted for data collection from 60 people from different universities, and the results were analysed using a descriptive method. Following the responses given by the respondents, it was noticed that a lot of ESL learners believed that using Blogs to improve vocabulary development is beneficial since it raises the degree of involvement in studying. The current research investigates the use of social constructivist theory in the teaching of ESL learners. The purpose of this study report is to demonstrate the statistically significant impact of the use of Blogs on the growth of learners' vocabulary. Finally, the article concluded that, in light of the descriptive study, the social constructivist method is very significant in English language learning, particularly in vocabulary development. The following objectives were established for the study through Descriptive Method of Social Constructivist Theory of Learning Vocabulary:•To explore the relationship between the use of Blogs and an interest in ESL learners' vocabulary knowledge.•To identify the effect of Blogs on the development of English vocabulary among ESL learners by using social constructivist theory.•To examine the effect of using Blogs on students' capacity to improve their vocabulary usage.

Analysis of Public Sentiment on COVID-19 Mitigation Measures in Social Media in the United States Using Machine Learning

Public sentiment can impact the implementation of public policies and even cause policy failure if public support is not received. Therefore, knowledge of public sentiment concerning new and emerging policies is critical for policymakers. During the coronavirus disease 2019 (COVID-19) pandemic, several precautionary measures have been suggested in an attempt to delay or mitigate the spread of the virus. This study presents a framework that applies natural language processing (NLP) techniques, such as sentiment and bigram analyses, to characterize the public sentiment on three prominent mitigation measures (mask wearing, social distancing, and quarantine) as shared by Twitter users in the United States. As part of the framework, we apply a bigram graph-based approach to visualize the most frequent topics in Twitter discussions during the COVID-19 pandemic. The objective is to provide insights into the most commonly discussed topics among Twitter users with similar demographic characteristics (e.g., age and gender). The sentiment and bigram analyses identified the most frequently discussed topics expressing both positive and negative sentiments among different age and gender groups. Discussions containing positive sentiment prevailed and revolved around the benefits of the measures and trust in the government, while the topics of negative sentiment involved conspiracy theories, skepticism, and distrust of government mandates. It is also notable that the discussions among people 19–29 and over 40 years old focus on government officials and political parties, benefits or inefficiency of mitigation measures, and conspiracy theories more often than other demographic groups. Our proposed approaches and results offer a novel and potentially valuable contribution to public policymakers. IEEE