Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

Between information campaign and controversy: a quantitative newspaper content analysis about COVID-19 vaccination in Switzerland and Austria

AIMS

Because media portrayal reflects and shapes public opinion and health policy, investigating news coverage of public health issues is highly relevant for public health research and practice. Addressing a topical issue, this study investigated how newspaper coverage framed COVID-19 vaccines in Austria and German-speaking Switzerland and how it developed over time.

METHODS

A quantitative newspaper content analysis of six newspapers from Austria and German-speaking Switzerland published between January 1 and 31, 2022 was conducted. Frames were identified for each country separately through hierarchical cluster analysis (Ward's method) based on frame elements.

RESULTS

Four frames were identified in both countries: (1) Evaluating new vaccines, (2) Discussing mandates, (3) Promoting vaccination, (4) Mentioning vaccines. In Frames 1 (Switzerland 86.4%, Austria 93.3%) and 3 (Switzerland 92.7%, Austria 98.9%), most articles included vaccine-endorsing statements, with Swiss coverage including additional negative statements more often than Austrian coverage (43.2%/44.6% vs 4.0%/3.3%). Frame 2 was closely linked to vaccine skepticism only in Austria and contained more evaluative statements in Austrian newspapers (25.4% endorsing, 35.4% rejecting; in Switzerland 14.5%/18.1%). The Austrian tabloid Kronen Zeitung published most articles (497/1091, 45.6%).

CONCLUSIONS

The commercialized and comparatively high share of tabloid news coverage in Austria may have contributed to oversimplified and polarizing COVID-19 vaccine debates in this context. Insufficiently balanced and adequate information may contribute to a loss of public trust in vaccination and may therefore affect vaccination uptake. Authorities and public health professionals should consider this effect when designing information campaigns.

Surveillance of Gun-Related Conversations on Twitter

Gun violence in the USA is a documented public health crisis. Publicly accessible data from Twitter posts can be used to rapidly capture and describe the public's recent conversations about guns. Because these gun-related conversations change rapidly, it is important to provide regularly updated information on them. Twitter posts containing gun-related terms were obtained from January 1, 2022 to June 30, 2022. To understand topics of gun-related tweets (N = 449,492), topic modeling was performed with Top2Vec. Gun ownership control, concern about gun safety and its impact on children and schools, and the Second Amendment were major areas of the gun-related discourse on Twitter. Several identified topics in this study were a consequence of the study period, including "Discourse on Capitol Riots," and "Wartime and Military Use of Guns," with the latter topic containing conversations about the Russia-Ukraine War. Conversations around the influence of the National Rifle Association (NRA) on gun policies and pro-gun ownership perspectives were also part of the public discourse. The intersection between alcohol, substance use, and gun use was infrequently observed. Findings suggest that gun-related conversations in social media such as Twitter can inform public health researchers.

Public Opinion About COVID-19 on a Microblog Platform in China: Topic Modeling and Multidimensional Sentiment Analysis of Social Media

BACKGROUND

The COVID-19 pandemic raised wide concern from all walks of life globally. Social media platforms became an important channel for information dissemination and an effective medium for public sentiment transmission during the COVID-19 pandemic.

OBJECTIVE

Mining and analyzing social media text information can not only reflect the changes in public sentiment characteristics during the COVID-19 pandemic but also help the government understand the trends in public opinion and reasonably control public opinion.

METHODS

First, this study collected microblog comments related to the COVID-19 pandemic as a data set. Second, sentiment analysis was carried out based on the topic modeling method combining latent Dirichlet allocation (LDA) and Bidirectional Encoder Representations from Transformers (BERT). Finally, a machine learning linear regression (ML-LR) model combined with a sparse matrix was proposed to explore the evolutionary trend in public opinion on social media and verify the high accuracy of the model.

RESULTS

The experimental results show that, in different stages, the characteristics of public emotion are different, and the overall trend is from negative to positive.

CONCLUSIONS

The proposed method can effectively reflect the characteristics of the different times and space of public opinion. The results provide theoretical support and practical reference in response to public health and safety events.

Beyond fear and anger: A global analysis of emotional response to Covid-19 news on Twitter using deep learning

The media has been used to disseminate public information amid the Covid-19 pandemic. However, the Covid-19 news has triggered emotional responses in people that have impacted their mental well-being and led to news avoidance. To understand the emotional response to the Covid-19 news, we study user comments on the news published on Twitter by 37 media outlets in 11 countries from January 2020 to December 2022. We employ a deep-learning-based model to identify one of the 6 Ekman's basic emotions, or the absence of emotional expression, in comments to the Covid-19 news, and an implementation of Latent Dirichlet Allocation (LDA) to identify 12 different topics in the news messages. Our analysis finds that while nearly half of the user comments show no significant emotions, negative emotions are more common. Anger is the most common emotion, particularly in the media and comments about political responses and governmental actions in the United States. Joy, on the other hand, is mainly linked to media outlets from the Philippines and news on vaccination. Over time, anger is consistently the most prevalent emotion, with fear being most prevalent at the start of the pandemic but decreasing and occasionally spiking with news of Covid-19 variants, cases, and deaths. Emotions also vary across media outlets, with Fox News having the highest level of disgust, the second-highest level of anger, and the lowest level of fear. Sadness is highest at Citizen TV, SABC, and Nation Africa, all three African media outlets. Also, fear is most evident in the comments to the news from The Times of India.

A two-staged NLP-based framework for assessing the sentiments on Indian supreme court judgments

Topic modeling is a powerful technique for uncovering hidden patterns in large documents. It can identify themes that are highly connected and lead to a certain region while accounting for temporal and spatial complexity. In addition, sentiment analysis can determine the sentiments of media articles on various issues. This study proposes a two-stage natural language processing-based model that utilizes Latent Dirichlet Allocation to identify critical topics related to each type of legal case or judgment and the Valence Aware Dictionary Sentiment Reasoner algorithm to assess people's sentiments on those topics. By applying these strategies, this research aims to influence public perception of controversial legal issues. This study is the first of its kind to use topic modeling and sentiment analysis on Indian legal documents and paves the way for a better understanding of legal documents.

CovTiNet: Covid text identification network using attention-based positional embedding feature fusion

Covid text identification (CTI) is a crucial research concern in natural language processing (NLP). Social and electronic media are simultaneously adding a large volume of Covid-affiliated text on the World Wide Web due to the effortless access to the Internet, electronic gadgets and the Covid outbreak. Most of these texts are uninformative and contain misinformation, disinformation and malinformation that create an infodemic. Thus, Covid text identification is essential for controlling societal distrust and panic. Though very little Covid-related research (such as Covid disinformation, misinformation and fake news) has been reported in high-resource languages (e.g. English), CTI in low-resource languages (like Bengali) is in the preliminary stage to date. However, automatic CTI in Bengali text is challenging due to the deficit of benchmark corpora, complex linguistic constructs, immense verb inflexions and scarcity of NLP tools. On the other hand, the manual processing of Bengali Covid texts is arduous and costly due to their messy or unstructured forms. This research proposes a deep learning-based network (CovTiNet) to identify Covid text in Bengali. The CovTiNet incorporates an attention-based position embedding feature fusion for text-to-feature representation and attention-based CNN for Covid text identification. Experimental results show that the proposed CovTiNet achieved the highest accuracy of 96.61±.001% on the developed dataset (BCovC) compared to the other methods and baselines (i.e. BERT-M, IndicBERT, ELECTRA-Bengali, DistilBERT-M, BiLSTM, DCNN, CNN, LSTM, VDCNN and ACNN).

Microblog Emotion Analysis Using Improved DBN Under Spark Platform

In order to solve the problems that traditional single-machine methods find it difficult to complete the task of emotion classification quickly, and the time efficiency and scalability are not high; a microblog emotion analysis method using improved deep belief network (DBN) under Spark platform is proposed. First, the Hadoop distributed file system is used to realize the distributed storage of text data, and the preprocessed data and emotion dictionary are converted into word vector representation based on the continuous bag-of-words model. Then, an improved DBN model is constructed by combining the adaptive learning method of DBN with the active learning method, and it is applied to the learning analysis of text word vectors. Finally, the data parallel optimization of the improved DBN model is realized, based on Spark platform to accurately and quickly obtain the emotion types of microblog texts. The experimental analysis of the proposed method based on the microblog text data set shows that the classification accuracy is more than 94%.

Covering the Crisis: Evolution of Key Topics and Actors in COVID-19 News Coverage in Switzerland

Objectives: The goal of this study is to map the share of COVID-related news articles over time, to investigate key subtopics and their evolution throughout the pandemic, and to identify key actors and their relationship with different aspects of the discourse around the pandemic.

Methods: This study uses a large-scale automated content analysis to conduct a within-country comparison of news articles (N = 1,171,114) from two language regions of Switzerland during the first 18 months of the pandemic.

Results: News media coverage of the pandemic largely mirrors key epidemiological developments in terms of the volume and content of coverage. Key actors in COVID-related reporting tend to be included in news articles that relate to their respective area of expertise.

Conclusion: Balanced news coverage of the pandemic facilitates effective dissemination of pandemic-related information by health authorities.

Text classification technique for discovering country-based publications from international COVID-19 publications

Objective

The significant increase in the number of COVID-19 publications, on the one hand, and the strategic importance of this subject area for research and treatment systems in the health field, on the other hand, reveals the need for text-mining research more than ever. The main objective of the present paper is to discover country-based publications from international COVID-19 publications with text classification techniques.

Methods

The present paper is applied research that has been performed using text-mining techniques such as clustering and text classification. The statistical population is all COVID-19 publications from PubMed Central® (PMC), extracted from November 2019 to June 2021. Latent Dirichlet allocation (LDA) was used for clustering, and support vector machine (SVM), scikit-learn library, and Python programming language were used for text classification. Text classification was applied to discover the consistency of Iranian and international topics.

Results

The findings showed that seven topics were extracted using the LDA algorithm for international and Iranian publications on COVID-19. Moreover, the COVID-19 publications show the largest share in the subject area of "Social and Technology in COVID-19" at the international (April 2021) and national (February 2021) levels with 50.61% and 39.44%, respectively. The highest rate of publications at international and national levels was in April 2021 and February 2021, respectively.

Conclusion

One of the most important results of this study was discovering a common trend and consistency of Iranian and international publications on COVID-19. Accordingly, in the topic category "Covid-19 Proteins: Vaccine and Antibody Response," Iranian publications have a common publishing and research trend with international ones.

Vaccines, media and politics: A corpus-assisted discourse study of press representations of the safety and efficacy of COVID-19 vaccines

This study gives a corpus-assisted discourse study of the representations of the safety and efficacy of COVID-19 vaccines in three representative newspapers from the US, Hong Kong, and the Chinese mainland: New York Times (NYT), South China Morning Post (SCMP), and China Daily (CD). The primary purpose is to explicate the dynamics between vaccines, media, and politics. Combining the theories and methods of critical discourse analysis and corpus linguistics, this study has revealed their preferential ways of constructing the safety and efficacy of COVID-19 vaccines at different levels of discourse. The safety and efficacy of COVID-19 vaccines thus serve as an important ideological battlefield for newspapers from different origins to advance their respective national or regional interests and shape understanding of different COVID-19 vaccines in the international arena.

Media Reports on COVID-19 Vaccinations: A Study of Topic Modeling in South Korea

Early successes in controlling the COVID-19 pandemic have prevented Republic of Korea from implementing a prompt, large-scale vaccine rollout to the public. The influence of traditional media on public opinion remains critical and substantial in Republic of Korea, and there have been heated debates about vaccination in traditional media reports in Korea. Effective and efficient public health communication is integral in managing public health challenges. This study explored media reports on the COVID-19 vaccines during the pandemic in Republic of Korea. 12,399 media news reports from May 2020 to September 2021 were collected. An LDA topic model was applied in order to analyze and compare the topics drawn from each study phase using words from the unstructured text data. Although media reports from before the national vaccination implementation focused on the development and rollout of COVID-19 vaccines, diverse topics were reported without any overlap. After the vaccination rollout, the biggest concern was the side effects of the COVID-19 vaccine. In sum, Republic of Korea's major media outlets reported on diverse topics rather than generating a common discourse about topics related to COVID-19 vaccination.

Enhanced sentiment analysis regarding COVID-19 news from global channels

For a healthy society to exist, it is crucial for the media to focus on disease-related issues so that more people are widely aware of them and reduce health risks. Recently, deep neural networks have become a popular tool for textual sentiment analysis, which can provide valuable insights and real-time monitoring and analysis regarding health issues. In this paper, as part of an effort to develop an effective model that can elicit public sentiment on COVID-19 news, we propose a novel approach Cov-Att-BiLSTM for sentiment analysis of COVID-19 news headlines using deep neural networks. We integrate attention mechanisms, embedding techniques, and semantic level data labeling into the prediction process to enhance the accuracy. To evaluate the proposed approach, we compared it to several deep and machine learning classifiers using various metrics of categorization efficiency and prediction quality, and the experimental results demonstrate its superiority with 0.931 testing accuracy. Furthermore, 73,138 pandemic-related tweets posted on six global channels were analyzed by the proposed approach, which accurately reflects global coverage of COVID-19 news and vaccination.

Framing of COVID-19 in Newspapers: A Perspective from the US-Mexico Border

The degree to which the media report a health emergency affects the seriousness with which the people respond to combat the health crisis. Engagement from local newspapers in the US has received scant scrutiny, even though there is a sizable body of scholarship on the analysis of COVID-19 news. We fill this void by focusing on the Rio Grande Valley area of the US-Mexico border. To understand the differences, we compared such local news coverage with the coverage of a national news outlet. After collecting the relevant news articles, we used sentiment analysis, rapid automatic keyword extraction (RAKE), and co-occurrence network analysis to examine the main themes and sentiments of COVID-19 news articles. The RAKE identified that county-specific news or local regulations are more prevalent among the key terms in The Monitor which are absent in USA Today. The co-occurrence network shows the coverage of the disruption of sports season in USA Today which is not present in The Monitor. The sentiment analysis presents fear emotion is more dominant in USA Today, but trust emotion becomes more prevalent in The Monitor news coverage. These findings show us that, although the subject of the health emergency is the same, local and national newspapers describe it in different ways, and the sentiments they convey are also not the same.

Agenda-Setting for COVID-19: A Study of Large-Scale Economic News Coverage Using Natural Language Processing

Over the past two years, organizations and businesses have been forced to constantly adapt and develop effective responses to the challenges of the COVID-19 pandemic. The acuteness, global scale and intense dynamism of the situation make online news and information even more important for making informed management and policy decisions. This paper focuses on the economic impact of the COVID-19 pandemic, using natural language processing (NLP) techniques to examine the news media as the main source of information and agenda-setters of public discourse over an eight-month period. The aim of this study is to understand which economic topics news media focused on alongside the dominant health coverage, which topics did not surface, and how these topics influenced each other and evolved over time and space. To this end, we used an extensive open-source dataset of over 350,000 media articles on non-medical aspects of COVID-19 retrieved from over 60 top-tier business blogs and news sites. We referred to the World Economic Forum’s Strategic Intelligence taxonomy to categorize the articles into a variety of topics. In doing so, we found that in the early days of COVID-19, the news media focused predominantly on reporting new cases, which tended to overshadow other topics, such as the economic impact of the virus. Different independent news sources reported on the same topics, showing a herd behavior of the news media during this global health crisis. However, a temporal analysis of news distribution in relation to its geographic focus showed that the rise in COVID-19 cases was associated with an increase in media coverage of relevant socio-economic topics. This research helps prepare for the prevention of social and economic crises when decision-makers closely monitor news coverage of viruses and related topics in other parts of the world. Thus, monitoring the news landscape on a global scale can support decision-making in social and economic crises. Our analyses point to ways in which this monitoring and issues management can be improved to remain alert to social dynamics and market changes.

Hate Speech in a Telegram Conspiracy Channel During the First Year of the COVID-19 Pandemic

Research has explored how the COVID-19 pandemic triggered a wave of conspiratorial thinking and online hate speech, but little is empirically known about how different phases of the pandemic are associated with hate speech against adversaries identified by online conspiracy communities. This study addresses this gap by combining observational methods with exploratory automated text analysis of content from an Italian-themed conspiracy channel on Telegram during the first year of the pandemic. We found that, before the first lockdown in early 2020, the primary target of hate was China, which was blamed for a new bioweapon. Yet over the course of 2020 and particularly after the beginning of the second lockdown, the primary targets became journalists and healthcare workers, who were blamed for exaggerating the threat of COVID-19. This study advances our understanding of the association between hate speech and a complex and protracted event like the COVID-19 pandemic, and it suggests that country-specific responses to the virus (e.g., lockdowns and re-openings) are associated with online hate speech against different adversaries depending on the social and political context.

Investigating Topic Modeling Techniques to Extract Meaningful Insights in Italian Long COVID Narration

Through an adequate survey of the history of the disease, Narrative Medicine (NM) aims to allow the definition and implementation of an effective, appropriate, and shared treatment path. In the present study different topic modeling techniques are compared, as Latent Dirichlet Allocation (LDA) and topic modeling based on BERT transformer, to extract meaningful insights in the Italian narration of COVID-19 pandemic. In particular, the main focus was the characterization of Post-acute Sequelae of COVID-19, (i.e., PASC) writings as opposed to writings by health professionals and general reflections on COVID-19, (i.e., non-PASC) writings, modeled as a semi-supervised task. The results show that the BERTopic-based approach outperforms the LDA-base approach by grouping in the same cluster the 97.26% of analyzed documents, and reaching an overall accuracy of 91.97%.

Reviewing topics of COVID-19 news articles: case study of CNN and China daily

Purpose

The purpose of this study is to analyze the topics of COVID-19 news articles for better obtaining the relationship among and the evolution of news topics, helping to manage the infodemic from a quantified perspective.

Design/methodology/approach

To analyze COVID-19 news articles explicitly, this paper proposes a prism architecture. Based on epidemic-related news on China Daily and CNN, this paper identifies the topics of the two news agencies, elucidates the relationship between and amongst these topics, tracks topic changes as the epidemic progresses and presents the results visually and compellingly.

Findings

The analysis results show that CNN has a more concentrated distribution of topics than China Daily, with the former focusing on government-related information, and the latter on medical. Besides, the pandemic has had a big impact on CNN and China Daily's reporting preference. The evolution analysis of news topics indicates that the dynamic changes of topics have a strong relationship with the pandemic process.

Originality/value

This paper offers novel perspectives to review the topics of COVID-19 news articles and provide new understandings of news articles during the initial outbreak. The analysis results expand the scope of infodemic-related studies.

A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts

The richness of social media data has opened a new avenue for social science research to gain insights into human behaviors and experiences. In particular, emerging data-driven approaches relying on topic models provide entirely new perspectives on interpreting social phenomena. However, the short, text-heavy, and unstructured nature of social media content often leads to methodological challenges in both data collection and analysis. In order to bridge the developing field of computational science and empirical social research, this study aims to evaluate the performance of four topic modeling techniques; namely latent Dirichlet allocation (LDA), non-negative matrix factorization (NMF), Top2Vec, and BERTopic. In view of the interplay between human relations and digital media, this research takes Twitter posts as the reference point and assesses the performance of different algorithms concerning their strengths and weaknesses in a social science context. Based on certain details during the analytical procedures and on quality issues, this research sheds light on the efficacy of using BERTopic and NMF to analyze Twitter data.

A Novel Approach of Feature Space Reconstruction with Three-Way Decisions for Long-Tailed Text Classification

Text classification is widely studied by researchers in the natural language processing field. However, real-world text data often follow a long-tailed distribution as the frequency of each class is typically different. The performance of current mainstream learning algorithms in text classification suffers when the training data are highly imbalanced. The problem can get worse when the categories with fewer data are severely undersampled to the extent that the variation within each category is not fully captured by the given data. At present, there are a few studies on long-tailed text classification which put forward effective solutions. Encouraged by the progress of handling long-tailed data in the field of image, we try to integrate effective ideas into the field of long-tailed text classification and prove the effectiveness. In this paper, we come up with a novel approach of feature space reconstruction with the help of three-way decisions (3WDs) for long-tailed text classification. In detail, we verify the rationality of using a 3WD model for feature selection in long-tailed text data classification, propose a new feature space reconstruction method for long-tailed text data for the first time, and demonstrate how to effectively generate new samples for tail classes in reconstructed feature space. By adding new samples, we enrich the representing information of tail classes, to improve the classification results of long-tailed text classification. After some comparative experiments, we have verified that our model is an effective strategy to improve the performance of long-tailed text classification.

Using ‘infodemics’ to understand public awareness and perception of SARS-CoV-2: A longitudinal analysis of online information about COVID-19 incidence and mortality during a major outbreak in Vietnam, July—September 2020

Background

Trends in the public perception and awareness of COVID-19 over time are poorly understood. We conducted a longitudinal study to analyze characteristics and trends of online information during a major COVID-19 outbreak in Da Nang province, Vietnam in July-August 2020 to understand public awareness and perceptions during an epidemic.

Methods

We collected online information on COVID-19 incidence and mortality from online platforms in Vietnam between 1 July and 15 September, 2020, and assessed their trends over time against the epidemic curve. We explored the associations between engagement, sentiment polarity, and other characteristics of online information with different outbreak phases using Poisson regression and multinomial logistic regression analysis. We assessed the frequency of keywords over time, and conducted a semantic analysis of keywords using word segmentation.

Results

We found a close association between collected online information and the evolution of the COVID-19 situation in Vietnam. Online information generated higher engagements during compared to before the outbreak. There was a close relationship between sentiment polarity and posts’ topics: the emotional tendencies about COVID-19 mortality were significantly more negative, and more neutral or positive about COVID-19 incidence. Online newspaper reported significantly more information in negative or positive sentiment than online forums or social media. Most topics of public concern followed closely the progression of the COVID-19 situation during the outbreak: development of the global pandemic and vaccination; the unfolding outbreak in Vietnam; and the subsiding of the outbreak after two months.

Conclusion

This study shows how online information can reflect a public health threat in real time, and provides important insights about public awareness and perception during different outbreak phases. Our findings can help public health decision makers in Vietnam and other low and middle income countries with high internet penetration rates to design more effective communication strategies during critical phases of an epidemic.

Gulf Countries’ Citizens’ Acceptance of COVID-19 Vaccines—A Machine Learning Approach

The COVID-19 pandemic created a global emergency in many sectors. The spread of the disease can be subdued through timely vaccination. The COVID-19 vaccination process in various countries is ongoing and is slowing down due to multiple factors. Many studies on European countries and the USA have been conducted and have highlighted the public’s concern that over-vaccination results in slowing the vaccination rate. Similarly, we analyzed a collection of data from the gulf countries’ citizens’ COVID-19 vaccine-related discourse shared on social media websites, mainly via Twitter. The people’s feedback regarding different types of vaccines needs to be considered to increase the vaccination process. In this paper, the concerns of Gulf countries’ people are highlighted to lessen the vaccine hesitancy. The proposed approach emphasizes the Gulf region-specific concerns related to COVID-19 vaccination accurately using machine learning (ML)-based methods. The collected data were filtered and tokenized to analyze the sentiments extracted using three different methods: Ratio, TextBlob, and VADER methods. The sentiment-scored data were classified into positive and negative tweeted data using a proposed LSTM method. Subsequently, to obtain more confidence in classification, the in-depth features from the proposed LSTM were extracted and given to four different ML classifiers. The ratio, TextBlob, and VADER sentiment scores were separately provided to LSTM and four machine learning classifiers. The VADER sentiment scores had the best classification results using fine-KNN and Ensemble boost with 94.01% classification accuracy. Given the improved accuracy, the proposed scheme is robust and confident in classifying and determining sentiments in Twitter discourse.

Exploring how online responses change in response to debunking messages about COVID-19 on WhatsApp

Purpose

The COVID-19 pandemic has spurred a concurrent outbreak of false information online. Debunking false information about a health crisis is critical as misinformation can trigger protests or panic, which necessitates a better understanding of it. This exploratory study examined the effects of debunking messages on a COVID-19-related public chat on WhatsApp in Singapore.

Design/methodology/approach

To understand the effects of debunking messages about COVID-19 on WhatsApp conversations, the following was studied. The relationship between source credibility (i.e. characteristics of a communicator that affect the receiver's acceptance of the message) of different debunking message types and their effects on the length of the conversation, sentiments towards various aspects of a crisis, and the information distortions in a message thread were studied. Deep learning techniques, knowledge graphs (KG), and content analyses were used to perform aspect-based sentiment analysis (ABSA) of the messages and measure information distortion.

Findings

Debunking messages with higher source credibility (e.g. providing evidence from authoritative sources like health authorities) help close a discussion thread earlier. Shifts in sentiments towards some aspects of the crisis highlight the value of ABSA in monitoring the effectiveness of debunking messages. Finally, debunking messages with lower source credibility (e.g. stating that the information is false without any substantiation) are likely to increase information distortion in conversation threads.

Originality/value

The study supports the importance of source credibility in debunking and an ABSA approach in analysing the effect of debunking messages during a health crisis, which have practical value for public agencies during a health crisis. Studying differences in the source credibility of debunking messages on WhatsApp is a novel shift from the existing approaches. Additionally, a novel approach to measuring information distortion using KGs was used to shed insights on how debunking can reduce information distortions.

Data-Driven Analytics Leveraging Artificial Intelligence in the Era of COVID-19: An Insightful Review of Recent Developments

This paper presents the role of artificial intelligence (AI) and other latest technologies that were employed to fight the recent pandemic (i.e., novel coronavirus disease-2019 (COVID-19)). These technologies assisted the early detection/diagnosis, trends analysis, intervention planning, healthcare burden forecasting, comorbidity analysis, and mitigation and control, to name a few. The key-enablers of these technologies was data that was obtained from heterogeneous sources (i.e., social networks (SN), internet of (medical) things (IoT/IoMT), cellular networks, transport usage, epidemiological investigations, and other digital/sensing platforms). To this end, we provide an insightful overview of the role of data-driven analytics leveraging AI in the era of COVID-19. Specifically, we discuss major services that AI can provide in the context of COVID-19 pandemic based on six grounds, (i) AI role in seven different epidemic containment strategies (a.k.a non-pharmaceutical interventions (NPIs)), (ii) AI role in data life cycle phases employed to control pandemic via digital solutions, (iii) AI role in performing analytics on heterogeneous types of data stemming from the COVID-19 pandemic, (iv) AI role in the healthcare sector in the context of COVID-19 pandemic, (v) general-purpose applications of AI in COVID-19 era, and (vi) AI role in drug design and repurposing (e.g., iteratively aligning protein spikes and applying three/four-fold symmetry to yield a low-resolution candidate template) against COVID-19. Further, we discuss the challenges involved in applying AI to the available data and privacy issues that can arise from personal data transitioning into cyberspace. We also provide a concise overview of other latest technologies that were increasingly applied to limit the spread of the ongoing pandemic. Finally, we discuss the avenues of future research in the respective area. This insightful review aims to highlight existing AI-based technological developments and future research dynamics in this area.

Mass Media as a Mirror of the COVID-19 Pandemic

The media plays an important role in disseminating facts and knowledge to the public at critical times, and the COVID-19 pandemic is a good example of such a period. This research is devoted to performing a comparative analysis of the representation of topics connected with the pandemic in the internet media of Kazakhstan and the Russian Federation. The main goal of the research is to propose a method that would make it possible to analyze the correlation between mass media dynamic indicators and the World Health Organization COVID-19 data. In order to solve the task, three approaches related to the representation of mass media dynamics in numerical form—automatically obtained topics, average sentiment, and dynamic indicators—were proposed and applied according to a manually selected list of search queries. The results of the analysis indicate similarities and differences in the ways in which the epidemiological situation is reflected in publications in Russia and in Kazakhstan. In particular, the publication activity in both countries correlates with the absolute indicators, such as the daily number of new infections, and the daily number of deaths. However, mass media tend to ignore the positive rate of confirmed cases and the virus reproduction rate. If we consider strictness of quarantine measures, mass media in Russia show a rather high correlation, while in Kazakhstan, the correlation is much lower. Analysis of search queries revealed that in Kazakhstan the problem of fake news and disinformation is more acute during periods of deterioration of the epidemiological situation, when the level of crime and poverty increase. The novelty of this work is the proposal and implementation of a method that allows the performing of a comparative analysis of objective COVID-19 statistics and several mass media indicators. In addition, it is the first time that such a comparative analysis, between different countries, has been performed on a corpus in a language other than English.

Real-Time Infoveillance of Moroccan Social Media Users' Sentiments towards the COVID-19 Pandemic and Its Management

The impact of COVID-19 on socio-economic fronts, public health related aspects and human interactions is undeniable. Amidst the social distancing protocols and the stay-at-home regulations imposed in several countries, citizens took to social media to cope with the emotional turmoil of the pandemic and respond to government issued regulations. In order to uncover the collective emotional response of Moroccan citizens to this pandemic and its effects, we use topic modeling to identify the most dominant COVID-19 related topics of interest amongst Moroccan social media users and sentiment/emotion analysis to gain insights into their reactions to various impactful events. The collected data consists of COVID-19 related comments posted on Twitter, Facebook and Youtube and on the websites of two popular online news outlets in Morocco (Hespress and Hibapress) throughout the year 2020. The comments are expressed in Moroccan Dialect (MD) or Modern Standard Arabic (MSA). To perform topic modeling and sentiment classification, we built a first Universal Language Model for the Moroccan Dialect (MD-ULM) using available corpora, which we have fine-tuned using our COVID-19 dataset. We show that our method significantly outperforms classical machine learning classification methods in Topic Modeling, Emotion Recognition and Polar Sentiment Analysis. To provide real-time infoveillance of these sentiments, we developed an online platform to automate the execution of the different processes, and in particular regular data collection. This platform is meant to be a decision-making assistance tool for COVID-19 mitigation and management in Morocco.

Investigating COVID-19 News before and after the Soft Lockdown: An Example from Taiwan

COVID-19 caused an unprecedented public health crisis and was declared a global pandemic on 11 March 2020, by the World Health Organization. The Taiwanese government’s early deployment mitigated the effect of the pandemic, yet the breakout in May 2021 brought a new challenge. This study focuses on examining Taiwanese newspaper articles regarding the government response before and after the soft lockdown, collecting 125,570 articles reported by three major news channels from 31 December 2019, to 30 June 2021, and splitting them into four stages. Latent Dirichlet Allocation topic modeling and sentiment analysis were used to depict the overall picture of Taiwan’s pandemic. While the news media focused on the impact and shock of the pandemic in the initial stage, prevention measures were more present in the last stage. Then, to focus on the government response indicators, we retrieved 31,089 related news from 125,570 news articles and categorized them into ten indicators, finding the news centered on the fundamental measures that were taken early and that were transformed into advanced measures in the latest and hardest period of the pandemic. Furthermore, this paper examines the temporal distribution of the news related to each indicator with the support of a sentiment analysis of the news’ titles and content, indicating the preparation of Taiwanese society to confront the pandemic.

Effects of the COVID-19 Pandemic on Classrooms: A Case Study on Foreigners in South Korea Using Applied Machine Learning

In this study, we qualitatively and quantitatively examine the effects of COVID-19 on classrooms, students, and educators. Using a new Twitter dataset specific to South Korea during the pandemic, we sample the sentiment and strain on students and educators using applied machine learning techniques in order to identify various topical pain points emerging during the pandemic. Our contributions include a novel and open source geo-fenced dataset on student and educator opinion within South Korea that we are making available to other researchers as well. We also identify trends in sentiment and polarity over the pandemic timeline, as well as key drivers behind the sentiments. Moreover, we provide a comparative analysis of two widely used pre-trained sentiment analysis approaches with TextBlob and VADER using statistical significance tests. Ultimately, we analyze how public opinion shifted on the pandemic in terms of positive sentiments about accessing course materials, online support communities, access to classes, and creativity, to negative sentiments about mental fatigue, job loss, student concerns, and overwhelmed institutions. We also initiate initial discussions about the concept of actionable sentiment analysis by overlapping polarity with the concept of trigger management to assist users in coping with negative emotions. We hope that insights from this preliminary study can promote further utilization of social media datasets to evaluate government messaging, population sentiment, and multi-dimensional analysis of pandemics.