An "Infodemic": Leveraging High-Volume Twitter Data to Understand Early Public Sentiment for the Coronavirus Disease 2019 Outbreak

An AI-enabled research support tool for the classification system of COVID-19

The outbreak of COVID-19, a little more than 2 years ago, drastically affected all segments of society throughout the world. While at one end, the microbiologists, virologists, and medical practitioners were trying to find the cure for the infection; the Governments were laying emphasis on precautionary measures like lockdowns to lower the spread of the virus. This pandemic is perhaps also the first one of its kind in history that has research articles in all possible areas as like: medicine, sociology, psychology, supply chain management, mathematical modeling, etc. A lot of work is still continuing in this area, which is very important also for better preparedness if such a situation arises in future. The objective of the present study is to build a research support tool that will help the researchers swiftly identify the relevant literature on a specific field or topic regarding COVID-19 through a hierarchical classification system. The three main tasks done during this study are data preparation, data annotation and text data classification through bi-directional long short-term memory (bi-LSTM).

Data-driven analytics of COVID-19 'infodemic'

The rampant of COVID-19 infodemic has almost been simultaneous with the outbreak of the pandemic. Many concerted efforts are made to mitigate its negative effect to information credibility and data legitimacy. Existing work mainly focuses on fact-checking algorithms or multi-class labeling models that are less aware of the intrinsic characteristics of the language. Nor is it discussed how such representations can account for the common psycho-socio-behavior of the information consumers. This work takes a data-driven analytical approach to (1) describe the prominent lexical and grammatical features of COVID-19 misinformation; (2) interpret the underlying (psycho-)linguistic triggers in terms of sentiment, power and activity based on the affective control theory; (3) study the feature indexing for anti-infodemic modeling. The results show distinct language generalization patterns of misinformation of favoring evaluative terms and multimedia devices in delivering a negative sentiment. Such appeals are effective to arouse people’s sympathy toward the vulnerable community and foment their spreading behavior.

Determining containment policy impacts on public sentiment during the pandemic using social media data

SignificanceFor effective pandemic response, policymakers need tools that can assess policy impacts in near real-time. This requires policymakers to monitor changes in public well-being due to policy interventions. Particularly, containment measures affect people's mental well-being, yet changes in public emotions and sentiments are challenging to assess. Our work provides a solution by using social media posts to compute salient concerns and daily public sentiment values as a proxy of mental well-being. We demonstrate how public sentiment and concerns are impacted by various containment policy sub-types. This approach provides key benefits of using a data-driven approach to identify public concerns and provides near real-time assessment of policy impacts by computing daily public sentiment based on postings on social media.

Trend clustering from COVID-19 tweets using graphical lasso-guided iterative principal component analysis

This article presents a method for trend clustering from tweets about coronavirus disease (COVID-19) to help us objectively review the past and make decisions about future countermeasures. We aim to avoid detecting usual trends based on seasonal events while detecting essential trends caused by the influence of COVID-19. To this aim, we regard daily changes in the frequencies of each word in tweets as time series signals and define time series signals with single peaks as target trends. To successfully cluster the target trends, we propose graphical lasso-guided iterative principal component analysis (GLIPCA). GLIPCA enables us to remove trends with indirect correlations generated by other essential trends. Moreover, GLIPCA overcomes the difficulty in the quantitative evaluation of the accuracy of trend clustering. Thus, GLIPCA's parameters are easier to determine than those of other clustering methods. We conducted experiments using Japanese tweets about COVID-19 from March 8, 2020, to May 7, 2020. The results show that GLIPCA successfully distinguished trends before and after the declaration of a state of emergency on April 7, 2020. In addition, the results reveal the international argument about whether the Tokyo 2020 Summer Olympics should be held. The results suggest the tremendous social impact of the words and actions of Japanese celebrities. Furthermore, the results suggest that people's attention moved from worry and fear of an unknown novel pneumonia to the need for medical care and a new lifestyle as well as the scientific characteristics of COVID-19.

CAViaR-WS-based HAN: conditional autoregressive value at risk-water sailfish-based hierarchical attention network for emotion classification in COVID-19 text review data

The Corona Virus Disease-2019 (COVID-19) pandemic has made a remarkable impact on economies and societies worldwide. With numerous procedures of social distancing and lockdowns, it becomes essential to know people's emotional responses on a very large scale. Thus, an effective emotion classification approach is developed using the proposed Conditional Autoregressive Value at Risk-Water Sailfish-based Hierarchical Attention Network (CAViaR-WS-based HAN) for classifying the emotions in the COVID-19 text review data. The proposed approach, named CAViaR-WS, is designed by the incorporation of Conditional Autoregressive Value at Risk-Sail Fish (CAViaR-SF) and Water Cycle Algorithm (WCA). Here, the significant features, such as mean, variance, entropy, Term Frequency-Inverse Document Frequency (TF-IDF), SentiWordNet features, and spam word-based features, are extracted to further processing. Based on the extracted features, feature fusion is accomplished using the RideNN. In addition, CAViaR-SF-based GAN is used to perform the spam classification, and then, the emotion classification is carried out using Hierarchal Attention Networks (HAN), where the training procedure of HAN is performed using proposed CAViaR-WS. Furthermore, the developed CAViaR-WS-based HAN offers effective performance results concerning precision, recall, and f-measure with the maximal values of 0.937, 0.958, and 0.948, respectively.

Comparing tweet sentiments in megacities using machine learning techniques: In the midst of COVID-19

COVID-19 was announced by the World Health Organization as a pandemic on March 11, 2020. Not only has COVID-19 struck the economy and public health, but it also has deep influences on people's feelings. Twitter, as an active social media, is a great database where we can investigate people's sentiments during this pandemic. By conducting sentiment analysis on Tweets using advanced machine learning techniques, this study aims to investigate how public sentiments respond to the pandemic from March 2 to May 21, 2020 in New York City, Los Angeles, London, and another six global mega-cities. Results showed that across cities, negative and positive Tweet sentiment clustered around mid-March and early May, respectively. Furthermore, positive sentiments of Tweets from New York City and London were positively correlated with stricter quarantine measures, although this correlation was not significant in Los Angeles. Meanwhile, Tweet sentiments of all three cities did not exhibit a strong correlation with new cases and hospitalization. Last but not least, we provide a qualitative analysis of the reasons behind differences in correlations shown above, along with a discussion of the polarizing effect of public policies on Tweet sentiments. Thus, the results of this study imply that Tweet sentiment is more sensitive to quarantine orders than reported statistics of COVID-19, especially in populous megacities where public transportation is heavily relied upon, which calls for prompt and effective quarantine measures during contagious disease outbreaks.

Ranking of Importance Measures of Tweet Communities: Application to Keyword Extraction From COVID-19 Tweets in Japan

This article presents a method that detects tweet communities with similar topics and ranks the communities by importance measures. By identifying the tweet communities that have high importance measures, it is possible for users to easily find important information about the coronavirus disease (COVID-19). Specifically, we first construct a community network, whose nodes are tweet communities obtained by applying a community detection method to a tweet network. The community network is constructed based on textual similarities between tweet communities and sizes of tweet communities. Second, we apply algorithms for calculating centrality to the community network. Because the obtained centrality is based on tweet community sizes as well, we call it the importance measure in distinction to conventional centrality. The importance measure can simultaneously evaluate the importance of topics in the entire data set and occupancy (or dominance) of tweet communities in the network structure. We conducted experiments by collecting Japanese tweets about COVID-19 from March 1, 2020 to May 15, 2020. The results show that the proposed method is able to extract keywords that have a high correlation with the number of people infected with COVID-19 in Japan. Because users can browse the keywords from a small number of central tweet communities, quick and easy understanding of important information becomes feasible.

Sentiment analysis on the impact of coronavirus in social life using the BERT model

Nowadays, the whole world is confronting an infectious disease called the coronavirus. No country remained untouched during this pandemic situation. Due to no exact treatment available, the disease has become a matter of seriousness for both the government and the public. As social distance is considered the most effective way to stay away from this disease. Therefore, to address the people eagerness about the Corona pandemic and to express their views, the trend of people has moved very fast towards social media. Twitter has emerged as one of the most popular platforms among those social media platforms. By studying the same eagerness and opinions of people to understand their mental state, we have done sentiment analysis using the BERT model on tweets. In this paper, we perform a sentiment analysis on two data sets; one data set is collected by tweets made by people from all over the world, and the other data set contains the tweets made by people of India. We have validated the accuracy of the emotion classification from the GitHub repository. The experimental results show that the validation accuracy is ≈ 94%.

COVID-19 Discourse on Twitter in Four Asian Countries: Case Study of Risk Communication

BACKGROUND

COVID-19, caused by SARS-CoV-2, has led to a global pandemic. The World Health Organization has also declared an infodemic (ie, a plethora of information regarding COVID-19 containing both false and accurate information circulated on the internet). Hence, it has become critical to test the veracity of information shared online and analyze the evolution of discussed topics among citizens related to the pandemic.

OBJECTIVE

This research analyzes the public discourse on COVID-19. It characterizes risk communication patterns in four Asian countries with outbreaks at varying degrees of severity: South Korea, Iran, Vietnam, and India.

METHODS

We collected tweets on COVID-19 from four Asian countries in the early phase of the disease outbreak from January to March 2020. The data set was collected by relevant keywords in each language, as suggested by locals. We present a method to automatically extract a time-topic cohesive relationship in an unsupervised fashion based on natural language processing. The extracted topics were evaluated qualitatively based on their semantic meanings.

RESULTS

This research found that each government's official phases of the epidemic were not well aligned with the degree of public attention represented by the daily tweet counts. Inspired by the issue-attention cycle theory, the presented natural language processing model can identify meaningful transition phases in the discussed topics among citizens. The analysis revealed an inverse relationship between the tweet count and topic diversity.

CONCLUSIONS

This paper compares similarities and differences of pandemic-related social media discourse in Asian countries. We observed multiple prominent peaks in the daily tweet counts across all countries, indicating multiple issue-attention cycles. Our analysis identified which topics the public concentrated on; some of these topics were related to misinformation and hate speech. These findings and the ability to quickly identify key topics can empower global efforts to fight against an infodemic during a pandemic.

Characterizing the COVID-19 Infodemic on Chinese Social Media: Exploratory Study

BACKGROUND

The COVID-19 infodemic has been disseminating rapidly on social media and posing a significant threat to people's health and governance systems.

OBJECTIVE

This study aimed to investigate and analyze posts related to COVID-19 misinformation on major Chinese social media platforms in order to characterize the COVID-19 infodemic.

METHODS

We collected posts related to COVID-19 misinformation published on major Chinese social media platforms from January 20 to May 28, 2020, by using PythonToolkit. We used content analysis to identify the quantity and source of prevalent posts and topic modeling to cluster themes related to the COVID-19 infodemic. Furthermore, we explored the quantity, sources, and theme characteristics of the COVID-19 infodemic over time.

RESULTS

The daily number of social media posts related to the COVID-19 infodemic was positively correlated with the daily number of newly confirmed (r=0.672, P<.01) and newly suspected (r=0.497, P<.01) COVID-19 cases. The COVID-19 infodemic showed a characteristic of gradual progress, which can be divided into 5 stages: incubation, outbreak, stalemate, control, and recovery. The sources of the COVID-19 infodemic can be divided into 5 types: chat platforms (1100/2745, 40.07%), video-sharing platforms (642/2745, 23.39%), news-sharing platforms (607/2745, 22.11%), health care platforms (239/2745, 8.71%), and Q&A platforms (157/2745, 5.72%), which slightly differed at each stage. The themes related to the COVID-19 infodemic were clustered into 8 categories: "conspiracy theories" (648/2745, 23.61%), "government response" (544/2745, 19.82%), "prevention action" (411/2745, 14.97%), "new cases" (365/2745, 13.30%), "transmission routes" (244/2745, 8.89%), "origin and nomenclature" (228/2745, 8.30%), "vaccines and medicines" (154/2745, 5.61%), and "symptoms and detection" (151/2745, 5.50%), which were prominently diverse at different stages. Additionally, the COVID-19 infodemic showed the characteristic of repeated fluctuations.

CONCLUSIONS

Our study found that the COVID-19 infodemic on Chinese social media was characterized by gradual progress, videoization, and repeated fluctuations. Furthermore, our findings suggest that the COVID-19 infodemic is paralleled to the propagation of the COVID-19 epidemic. We have tracked the COVID-19 infodemic across Chinese social media, providing critical new insights into the characteristics of the infodemic and pointing out opportunities for preventing and controlling the COVID-19 infodemic.

An Exploratory Study of COVID-19 Information on Twitter in the Greater Region

The outbreak of the COVID-19 led to a burst of information in major online social networks (OSNs). Facing this constantly changing situation, OSNs have become an essential platform for people expressing opinions and seeking up-to-the-minute information. Thus, discussions on OSNs may become a reflection of reality. This paper aims to figure out how Twitter users in the Greater Region (GR) and related countries react differently over time through conducting a data-driven exploratory study of COVID-19 information using machine learning and representation learning methods. We find that tweet volume and COVID-19 cases in GR and related countries are correlated, but this correlation only exists in a particular period of the pandemic. Moreover, we plot the changing of topics in each country and region from 22 January 2020 to 5 June 2020, figuring out the main differences between GR and related countries.

Analysis and Evaluation of COVID-19 Web Applications for Health Professionals: Challenges and Opportunities

The multidisciplinary nature of the work required for research in the COVID-19 pandemic has created new challenges for health professionals in the battle against the virus. They need to be equipped with novel tools, applications, and resources-that have emerged during the pandemic-to gain access to breakthrough findings; know the latest developments; and to address their specific needs for rapid data acquisition, analysis, evaluation, and reporting. Because of the complex nature of the virus, healthcare systems worldwide are severely impacted as the treatment and the vaccine for COVID-19 disease are not yet discovered. This leads to frequent changes in regulations and policies by governments and international organizations. Our analysis suggests that given the abundance of information sources, finding the most suitable application for analysis, evaluation, or reporting, is one of such challenges. However, health professionals and policy-makers need access to the most relevant, reliable, trusted, and latest information and applications that can be used in their day-to-day tasks of COVID-19 research and analysis. In this article, we present our analysis of various novel and important web-based applications that have been specifically developed during the COVID-19 pandemic and that can be used by the health professionals community to help in advancing their analysis and research. These applications comprise search portals and their associated information repositories for literature and clinical trials, data sources, tracking dashboards, and forecasting models. We present a list of the minimally essential online, web-based applications to serve a multitude of purposes, from hundreds of those developed since the beginning of the pandemic. A critical analysis is provided for the selected applications based on 17 features that can be useful for researchers and analysts for their evaluations. These features make up our evaluation framework and have not been used previously for analysis and evaluation. Therefore, knowledge of these applications will not only increase productivity but will also allow us to explore new dimensions for using existing applications with more control, better management, and greater outcome of their research. In addition, the features used in our framework can be applied for future evaluations of similar applications and health professionals can adapt them for evaluation of other applications not covered in this analysis.

Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature

BACKGROUND

The COVID-19 pandemic is favoring digital transitions in many industries and in society as a whole. Health care organizations have responded to the first phase of the pandemic by rapidly adopting digital solutions and advanced technology tools.

OBJECTIVE

The aim of this review is to describe the digital solutions that have been reported in the early scientific literature to mitigate the impact of COVID-19 on individuals and health systems.

METHODS

We conducted a systematic review of early COVID-19-related literature (from January 1 to April 30, 2020) by searching MEDLINE and medRxiv with appropriate terms to find relevant literature on the use of digital technologies in response to the pandemic. We extracted study characteristics such as the paper title, journal, and publication date, and we categorized the retrieved papers by the type of technology and patient needs addressed. We built a scoring rubric by cross-classifying the patient needs with the type of technology. We also extracted information and classified each technology reported by the selected articles according to health care system target, grade of innovation, and scalability to other geographical areas.

RESULTS

The search identified 269 articles, of which 124 full-text articles were assessed and included in the review after screening. Most of the selected articles addressed the use of digital technologies for diagnosis, surveillance, and prevention. We report that most of these digital solutions and innovative technologies have been proposed for the diagnosis of COVID-19. In particular, within the reviewed articles, we identified numerous suggestions on the use of artificial intelligence (AI)-powered tools for the diagnosis and screening of COVID-19. Digital technologies are also useful for prevention and surveillance measures, such as contact-tracing apps and monitoring of internet searches and social media usage. Fewer scientific contributions address the use of digital technologies for lifestyle empowerment or patient engagement.

CONCLUSIONS

In the field of diagnosis, digital solutions that integrate with traditional methods, such as AI-based diagnostic algorithms based both on imaging and clinical data, appear to be promising. For surveillance, digital apps have already proven their effectiveness; however, problems related to privacy and usability remain. For other patient needs, several solutions have been proposed, such as telemedicine or telehealth tools. These tools have long been available, but this historical moment may actually be favoring their definitive large-scale adoption. It is worth taking advantage of the impetus provided by the crisis; it is also important to keep track of the digital solutions currently being proposed to implement best practices and models of care in future and to adopt at least some of the solutions proposed in the scientific literature, especially in national health systems, which have proved to be particularly resistant to the digital transition in recent years.

Causal Modeling of Twitter Activity during COVID-19

Understanding the characteristics of public attention and sentiment is an essential prerequisite for appropriate crisis management during adverse health events. This is even more crucial during a pandemic such as COVID-19, as primary responsibility of risk management is not centralized to a single institution, but distributed across society. While numerous studies utilize Twitter data in descriptive or predictive context during COVID-19 pandemic, causal modeling of public attention has not been investigated. In this study, we propose a causal inference approach to discover and quantify causal relationships between pandemic characteristics (e.g., number of infections and deaths) and Twitter activity as well as public sentiment. Our results show that the proposed method can successfully capture the epidemiological domain knowledge and identify variables that affect public attention and sentiment. We believe our work contributes to the field of infodemiology by distinguishing events that correlate with public attention from events that cause public attention.

Exploring Casual COVID-19 Data Visualizations on Twitter: Topics and Challenges

Social networking sites such as Twitter have been a popular choice for people to express their opinions, report real-life events, and provide a perspective on what is happening around the world. In the outbreak of the COVID-19 pandemic, people have used Twitter to spontaneously share data visualizations from news outlets and government agencies and to post casual data visualizations that they individually crafted. We conducted a Twitter crawl of 5409 visualizations (from the period between 14 April 2020 and 9 May 2020) to capture what people are posting. Our study explores what people are posting, what they retweet the most, and the challenges that may arise when interpreting COVID-19 data visualization on Twitter. Our findings show that multiple factors, such as the source of the data, who created the chart (individual vs. organization), the type of visualization, and the variables on the chart influence the retweet count of the original post. We identify and discuss five challenges that arise when interpreting these casual data visualizations, and discuss recommendations that should be considered by Twitter users while designing COVID-19 data visualizations to facilitate data interpretation and to avoid the spread of misconceptions and confusion.

Fighting fake news in the COVID-19 era: policy insights from an equilibrium model

The COVID-19 crisis has revealed structural failures in governance and coordination on a global scale. With related policy interventions dependent on verifiable evidence, pandemics require governments to not only consider the input of experts but also ensure that science is translated for public understanding. However, misinformation and fake news, including content shared through social media, compromise the efficacy of evidence-based policy interventions and undermine the credibility of scientific expertise with potentially longer-term consequences. We introduce a formal mathematical model to understand factors influencing the behavior of social media users when encountering fake news. The model illustrates that direct efforts by social media platforms and governments, along with informal pressure from social networks, can reduce the likelihood that users who encounter fake news embrace and further circulate it. This study has implications at a practical level for crisis response in politically fractious settings and at a theoretical level for research about post-truth and the construction of fact.

Corona and value change. The role of social media and emotional contagion

People share their emotions on social media and evidence suggests that in times of crisis people are especially motivated to post emotional content. The current Coronavirus pandemic is such a crisis. The online sharing of emotional content during the Coronavirus crisis may contribute to societal value change. Emotion sharing via social media could lead to emotional contagion which in turn could facilitate an emotional climate in a society. In turn, the emotional climate of a society can influence society's value structure. The emotions that spread in the current Coronavirus crisis are predominantly negative, which could result in a negative emotional climate. Based on the dynamic relations of values to each other and the way that emotions relate to values, a negative emotional climate can contribute to societal value change towards values related to security preservation and threat avoidance. As a consequence, a negative emotional climate and the shift in values could lead to a change in political attitudes that has implications for rights, freedom, privacy and moral progress. Considering the impact of social media in terms of emotional contagion and a longer-lasting value change is an important perspective in thinking about the ethical long-term impact of social media technology.

Communicating health crisis: a content analysis of global media framing of COVID-19

Background: This study examines the global media framing of coronavirus disease 2019(COVID-19) to understand the dominant frames and how choice of words compares in the media. Periods of health crisis such as the outbreak of coronavirus pandemic add to the enormous burden of the media in keeping people constantly informed. Extant literature suggests that when a message is released through the media, what matters most is not what is said but how it is said. As such, the media could either mitigate or accentuate the crisis depending on the major frames adopted for the coverage. Methods: The study utilises content analysis. Data were sourced from LexisNexis database and two websites that yielded 6145 items used for the analysis. Nine predetermined frames were used for the coding. Results: Human Interest and fear/scaremongering frames dominated the global media coverage of the pandemic. We align our finding with the constructionist frame perspective which assumes that the media as information processor creates 'interpretative packages' in order to both reflect and add to the 'issue culture' because frames that paradigmatically dominate event coverage also dominate audience response. The language of the coverage of COVID-19 combines gloom, hope, precaution and frustration at varied proportions. Conclusion: We conclude that global media coverage of COVID-19 was high, but the framing lacks coherence and sufficient self-efficacy and this can be associated with media's obsession for breaking news. The preponderance of these frames not only shapes public perception and attitudes towards the pandemic but also risks causing more problems for those with existing health conditions due to fear or panic attack.

Event Detection System Based on User Behavior Changes in Online Social Networks: Case of the COVID-19 Pandemic

People use Online Social Networks (OSNs) to express their opinions and feelings about many topics. Depending on the nature of an event and its dissemination rate in OSNs, and considering specific regions, the users' behavior can drastically change over a specific period of time. In this context, this work aims to propose an event detection system at the early stages of an event based on changes in the users' behavior in an OSN. This system can detect an event of any subject, and thus, it can be used for different purposes. The proposed event detection system is composed of the following main modules: (1) determination of the user's location, (2) message extraction from an OSN, (3) topic identification using natural language processing (NLP) based on the Deep Belief Network (DBN), (4) the user behavior change analyzer in the OSN, and (5) affective analysis for emotion identification based on a tree-convolutional neural network (tree-CNN). In the case of public health, the early event detection is very relevant for the population and the authorities in order to be able take corrective actions. Hence, the new coronavirus disease (COVID-19) is used as a case study in this work. For performance validation, the modules related to the topic identification and affective analysis were compared with other similar solutions or implemented with other machine learning algorithms. In the performance assessment, the proposed event detection system achieved an accuracy higher than 0.90, while other similar methods reached accuracy values less than 0.74. Additionally, our proposed system was able to detect an event almost three days earlier than the other methods. Furthermore, the information provided by the system permits to understand the predominant characteristics of an event, such as keywords and emotion type of messages.