A Classification Approach to Detect Public Sentiments towards COVID-19 Vaccines

In this paper, team University of Botswana Computer Science (UBCS) investigate the opinions of Twitter users towards vaccine uptake. In particular, we build three different text classifiers to detect people's opinions and classify them as provax-for opinions that are for vaccination, antivax for opinions against vaccination and neutral-for opinions that are neither for or against vaccination. Two different datasets obtained from Twitter, 1 by Cotfas and the other by Fire2022 Organizing team were merged to and used for this study. The dataset contained 4392 tweets. Our first classifier was based on the basic BERT model and the other 2 were machine learning models, Random Forest and Multinomial Naive Bayes models. Naive Bayes classifier outperformed other classifiers with a macro-F1 score of 0.319. © 2022 Copyright for this paper by its authors.

Demystifying the Impact of COVID-19 on Structural Volatility of Indian Sectoral Market: A Quantile Regression Analysis

The present study explores the impact of COVID-19 on the volatility structure of the sectoral market in India. ARMA(p,q)- GJR-GARCH(1, 1)-std model is used to determine the daily conditional volatility for 13 selected sectors over the period starting from January 2020 to December 2021. The quantile regression model is employed to examine the changes in the structure of volatility in each sector over the pandemic duration. The results of the study show that the volatility of Metal, Oil–Gas and PSU are more sensitive to market volatility, whereas the volume of new COVID-19 cases exceeds the threshold limit, and no extreme spillover is observed from the market volatility. In addition to this, Bankex, Metal, Oil–Gas, Private Banks and Power sector volatility are more responsive to news sentiments during the period of increase in new COVID-19 cases. Furthermore, the results also reveal that news sentiments help to control the significant fluctuation in the sectoral market. © 2023 MDI.

Maintainers of Stability: The Labor of China's Data-Driven Governance and Dynamic Zero-COVID

This paper examines the social, technological, and emotional labor of maintaining China's data-driven governance broadly, and dynamic zero-COVID management in particular. Drawing on ethnographic research in China, we examine the sociotechnical work of maintenance during the 2022 Shanghai lockdown. This labor included coordinating mass testing, quarantine, and lockdown procedures as well as implementing ad-hoc technological workarounds and managing public sentiments. We demonstrate that, far from being effected from the top down, China's data-driven governance relies on the circumscribed participation of citizens. During Shanghai's lockdown, citizens with relevant expertise helped to maintain technological stability by fixing or programming data systems, but also to ensure the ongoing production of"positive feelings"about social stability through data-driven governance. In so doing, such citizens simultaneously enacted an ambivalent and circumscribed form of agency, and maintained social and by extension political stability. This article sheds light on data-driven governance and political processes of maintenance. © 2023 ACM.

Food insufficiency and Twitter emotions during a pandemic.

The COVID-19 pandemic initially caused worldwide concerns about food insecurity. Tweets analyzed in real-time may help food assistance providers target food supplies to where they are most urgently needed. In this exploratory study, we use natural language processing to extract sentiments and emotions expressed in food security-related tweets early in the pandemic in U.S. states. The emotion joy dominated in these tweets nationally, but only anger, disgust, and fear were also statistically correlated with contemporaneous food insufficiency rates reported in the Household Pulse Survey; more nuanced and statistically stronger correlations are detected within states, including a negative correlation with joy.

Impact of COVID-19 pandemic on health workers sentiment towards influenza vaccination: A literature review

INTRODUCTION The COVID-19 era highlighted vaccine hesitancy (VH) among health workers (HWs) as a major hurdle to optimum immunization practices. Through the identification of relevant determinants, barriers, and interventions to counteract VH, this literature review examines the impact of the COVID-19 pandemic on HWs' influenza vaccination sentiment. METHODS Studies were identified by searching the PubMed database for articles published between August 2019 and July 2022. The search was restricted to articles in English that were original studies or meta-analyses or reviews. They were included in the review if they covered influenza VH among HWs during the COVID-19 pandemic. Inductive content analysis was used to identify themes that illustrate facilitators, barriers, and consideration. Risk of bias was not assessed. RESULTS Of 924 articles identified, 20 were selected. Of these, 15 were conducted in Europe and focused on healthcare staff, primarily in hospital settings. Within the COVID-19 context, physicians and residents were more willing than nurses to adhere to influenza vaccination. Young HWs, particularly males and those with chronic comorbidities, demonstrated the highest acceptance of the influenza vaccine. HWs' immunization history is associated with higher influenza vaccine adherence. Factors determining HW's acceptance of flu immunization were: healthcare staff's knowledge of the influenza vaccine, concerns about protecting themselves or others, and the rising perception of risk and fear from COVID-19 infection. Main barriers were negative perceptions about vaccine safety and effectiveness, insufficient time for vaccine uptake, and confidence in natural or acquired immunity. In the context of the pandemic, awareness campaigns and targeting vaccine affordability and accessibility were the most adopted interventions to increase vaccine acceptance amongst HWs. CONCLUSIONS In the context of COVID-19, confidence in influenza vaccines and the perception of risk from COVID-19 infection have increased among healthcare staff. To further explore the impact of the pandemic on HWs' sentiment toward influenza vaccination, conducting new empirical studies are strongly recommended © 2023 Meckawy R. et al. This is an Open Access article distributed under the terms of the Creative Commons Attribution NonCommercial 4.0 International License. (http://creativecommons.org/licenses/by-nc/4.0)

Analysis of Learners' Sentiments on MOOC Forums using Natural Language Processing Techniques

MOOCs have gained a lot of popularity for past few years. Especially after the outbreak of Coronavirus, everyone is trying to gain some knowledge and skill while being at the comfort of home and making themselves safe. Due to sudden increase in the number of participants on MOOCs there is a need for an automated system to be able to assess the reviews and feedbacks given by the learners and find the sentiments behind their statements. This analysis will help trainers identify their shortcoming and make their courses even better. For sentiments analysis, several approaches may be used. This research aims to provide a system which will perform sentiments analysis on the novel dataset and show the comparison of lexicon-based vs transformer-based sentiment analysis models. For lexicon based, VADER was chosen and for transformer-based, state-of-The-Art BERT was chosen. BERT was found to be exceptionally good with an accuracy of 84% and F1-score of 0.64. © 2022 IEEE.

[Sentiments in the COVID-19 crisis communication of German authorities and independent experts on Twitter : A sentiment analysis for the first year of the pandemic]. / Emotionalität in der COVID-19-Krisenkommunikation von Behörden und unabhängigen Expert*innen auf Twitter : Eine Sentiment-Analyse für das erste Pandemiejahr.

BACKGROUND: At the beginning of the COVID­19 pandemic in Germany, there was great uncertainty among the population and among those responsible for crisis communication. A substantial part of the communication from experts and the responsible authorities took place on social media, especially on Twitter. The positive, negative, and neutral sentiments (emotions) conveyed there during crisis communication have not yet been comparatively studied for Germany. STUDY AIM: Sentiments in Twitter messages from various (health) authorities and independent experts on COVID­19 will be evaluated for the first pandemic year (1 January 2020 to 15 January 2021) to provide a knowledge base for improving future crisis communication. MATERIAL AND METHODS: From n = 39 Twitter actors (21 authorities and 18 experts), n = 8251 tweets were included in the analysis. The sentiment analysis was done using the so-called lexicon approach, a method within the social media analytics framework to detect sentiments. Descriptive statistics were calculated to determine, among other things, the average polarity of sentiments and the frequencies of positive and negative words in the three phases of the pandemic. RESULTS AND DISCUSSION: The development of emotionality in COVID­19 tweets and the number of new infections in Germany run roughly parallel. The analysis shows that the polarity of sentiments is negative on average for both groups of actors. Experts tweet significantly more negatively about COVID­19 than authorities during the study period. Authorities communicate close to the neutrality line in the second phase, that is, neither distinctly positive nor negative.

Multimodal negative sentiment recognition of online public opinion on public health emergencies based on graph convolutional networks and ensemble learning

To improve the effect of multimodal negative sentiment recognition of online public opinion on public health emergencies, we constructed a novel multimodal fine-grained negative sentiment recognition model based on graph convolutional networks (GCN) and ensemble learning. This model comprises BERT and ViT-based multimodal feature representation, GCN-based feature fusion, multiple classifiers, and ensemble learning-based decision fusion. Firstly, the image-text data about COVID-19 is collected from Sina Weibo, and the text and image features are extracted through BERT and ViT, respectively. Secondly, the image-text fused features are generated through GCN in the constructed microblog graph. Finally, AdaBoost is trained to decide the final sentiments recognized by the best classifiers in image, text, and image-text fused features. The results show that the F1-score of this model is 84.13% in sentiment polarity recognition and 82.06% in fine-grained negative sentiment recognition, improved by 4.13% and 7.55% compared to the optimal recognition effect of image-text feature fusion, respectively. © 2023 Elsevier Ltd

Internet Governance: Social Mentality and Public Emotion Analysis on Online Media during the COVID-19 Epidemic in Mainland China

Based on a systematical discussion of the logical relationship between social mentality as a psychological basis of social actions and institutions and social governance, and the online emotion as the core element of the dynamic tendency of internet-based social mentality to form emotional energy to promote the operation of the internet society, this paper conducts an empirical study on the online social mentality and public sentiment guidance during the COVID-19 epidemic in mainland China. We use more than 1 million Weibo dynamic data of 104 accounts of three different types including official media, self-media, and big V media and conduct emotional calculation and judgment to address our objectives. The results show that the public sentiment presented by Weibo as the carrier is mainly positive, among which the official media play a positive role in guiding emotions, while the role played by big Vs' is limited during the COVID-19 epidemic. There exists different public sentiment stemmed from the regional differences brought by the heterogeneity of social governance, economic and social development beyond the media guidance. The study provides valuable internet governance experience on how the government can guide the public to respond to and deal with the crisis with a positive attitude when major public health emergencies occur in the future. © 2022 IEEE.

Twitter Data Sentiment Analysis of COVID-19 Vaccination using Machine Learning

The expansion of the web is accelerating, which helps encourage the creation of fresh ideas. In today's internet era, we must suggest techniques to filter out various information. Social media sentiment analysis based on Twitter data can monitor the real-Time monitoring of the COVID-19 vaccine. In this way, relevant organizations or governments can take proactive steps to address misinformation and inappropriate behaviour around the COVID-19 vaccine, which threatens the success of the national vaccination campaign. The purpose of this research is to determine if there is a link between how people feel about the COVID-19 vaccine on Twitter and how many people actually get vaccinated against it. This study uses the COVID-19 All Vaccines Tweet dataset sourced from Kaggle. This research Identifies public sentiment, emotion, word usage, and trend of all filtered tweets. The results show that there are 31% positive tweets, 10% negative tweets, and 58% neutral tweets. Tweets with neutral subjective valence tend to cluster in the middle of the polarity scale (between-1 and +1), whereas tweets with strong subjective valence are spread across the scale. © 2022 IEEE.

Do SEC filings indicate any trends? Evidence from the sentiment distribution of forms 10-K and 10-Q with FinBERT

Purpose: This study quantified companies' views on the COVID-19 pandemic with sentiment analysis of US public companies' disclosures. The study aims to provide timely insights to shareholders, investors and consumers by exploring sentiment trends and changes in the industry and the relationship with stock price indices. Design/methodology/approach: From more than 50,000 Form 10-K and Form 10-Q published between 2020 and 2021, over one million texts related to the COVID-19 pandemic were extracted. Applying the FinBERT fine-tuned for this study, the texts were classified into positive, negative and neutral sentiments. The correlations between sentiment trends, differences in sentiment distribution by industry and stock price indices were investigated by statistically testing the changes and distribution of quantified sentiments. Findings: First, there were quantitative changes in texts related to the COVID-19 pandemic in the US companies' disclosures. In addition, the changes in the trend of positive and negative sentiments were found. Second, industry patterns of positive and negative sentiment changes were similar, but no similarities were found in neutral sentiments. Third, in analyzing the relationship between the representative US stock indices and the sentiment trends, the results indicated a positive relationship with positive sentiments and a negative relationship with negative sentiments. Originality/value: Performing sentiment analysis on formal documents like Securities and Exchange Commission (SEC) filings, this study was differentiated from previous studies by revealing the quantitative changes of sentiment implied in the documents and the trend over time. Moreover, an appropriate data preprocessing procedure and analysis method were presented for the time-series analysis of the SEC filings. © 2022, Emerald Publishing Limited.

Sentiment Analysis towards Face-to-Face School Activities during the COVID-19 pandemic in Indonesia

As the COVID-19 pandemic took place, many face-to-face activities have been stopped to suppress the spread. However, in the last few months, many of those activities including learning activities have started to switch from online back to face-to-face. One of the major activities is face-to-face learning activities which involve millions of students all over Indonesia. Consequently, this study focuses on analyzing public sentiment through Twitter tweets which were obtained through scrapping by using Tweepy. The tweets were labeled using a semi-automatic process, using TextBlob and manual annotation. Next, we trained an IndoBERT model to conduct sentiment analysis and found that public sentiment was dominated by a mix of both negative and positive sentiment, followed by neutral sentiment. Our model obtained an accuracy of 40.79% on unseen data. © 2022 IEEE.

Comparison of K-Nearest Neighbor and Logistic Regression Algorithms on Sentiment Analysis of Covid-19 Vaccination on Twitter with Vader And Textblob Labeling

In this analysis, the methods used are the K-Nearest Neighbor classification method and the Logistic Regression classification method with data taken on the twitter application. This study examines the level of accuracy in public sentiment regarding covid-19 vaccination with positive and negative labels. The AUC value in the KNN algorithm with TextBlob labeling is 0.765 with and 0.76S for VaderSentiment labeling are both included in the fair classification criteria. Meanwhile, the Logistic Regression algorithm produces an accuracy of 84.97% with a ratio of 90:10 for Labeling TextBlob, while for Labeling VaderSentiment with a ratio of 90:10 results in an accuracy of 85.22%. Both algorithms are validated using K-Fold Cross Validation with a fold count of 10. The comparison results obtained when conducting an evaluation with the confusion matrix showed that the Logistic Regression algorithm with VaderSentiment labeling had the highest accuracy value compared to the K-Nearest Neighbor algorithm with TextBlob and VaderSentiment labeling. © 2022 IEEE.

Social Media, Emotions and Technology: Identifying Possibilities and Attitudes during the COVID-19 Pandemic

The disruption of the COVID-19 pandemic and its multiple challenges tested states, countries, and people. Regarding the latter, information, and communication technologies, together with social media platforms, became a resource that helped to reduce the shortcomings that arose because of the criticality at that moment. However, they also contributed to redirecting the emotional dimensions towards the digital space. This work proposes a novel approach to the case of Panama, by estimating the emotivity through opinion mining. The study used as a reactive element the official announcements issued by the Ministerio de Salud (Ministry of Health) related to the pandemic. The resulting reactions were recorded for six months through a popular social media platform. The results indicate a strong and negative impact on people's sensitivity. In addition, the data acquisition methods used, their processing, and analysis are provided as valuable contributions to the Latin American context for similar studies. © 2022 IEEE.

The Data Leakage Sentiment Analysis Using Naive Bayes Algorithm Based on Machine Learning Approach

Data leakage is a case that often occurs anywhere. Indonesia is one of the countries with the most population that is currently having data leakage cases. The leak of data on the COVID-19 PeduliLindung tracking application, triggered a public reaction because it was considered dangerous. Based on this, the aim of the study is to predict the sentiment pattern using Naïve Bayes. This study is important to do sentiment analysis to find out the public's reaction, it can become a recommendation in developing applications that are safer in data storage. The experiment in this study used data from Twitter which was taken for 14 days, between 16-21 May 2022. The data was processed using Google Collab and the Naïve Bayes approach. The experimental results are that negative sentiment is greater than positive sentiment and neutral sentiment, which is 93%. While the accuracy of positive sentiment is 81% and Neutra sentiment is 90%. This means the leak of public data from a COVID-19 tracing application in Indonesia has a greater negative sentiment. The difference in the study is the data testing process was carried out five times to get good accuracy from the model. And the results show that Naïve Bayes is a model that is quite recommended for prediction of sentiment patterns. © 2022 IEEE.

Dynamic impacts of online investor sentiment on international crude oil prices

In recent years, international crude oil prices have been subject to unusually high fluctuations due to the ravages of the COVID-19 epidemic. Under such extreme market conditions, online investor sentiment can strengthen the correlation between oil price changes and external events. We use a (rolling-window) structural vector autoregression method to investigate the dynamic impact of online investor sentiment on WTI crude oil prices before and after the COVID-19 pandemic across multiple topics of price, supply, demand, and so on, which aims to explore the fluctuation mechanism driven by sentiment and the price changes triggered by public health events. The proposed aspect-level sentiment analysis approach can effectively distinguish and measure sentiment scores of different aspects of the oil market. Our results show that the constructed oil price prosperity index contributes 49.84% to the long-term fluctuations of WTI oil price, ranking first among the influencing factors considered. In addition, the peak value of impulse shocks to WTI oil prices rose from 6.47% to 8.40% during the period of dramatic price volatility caused by the epidemic. The results sketch the mechanisms by which investor sentiment can affect crude oil prices, which help policymakers and investors protect against extreme risks in the oil market. © 2023 Elsevier Ltd

Sentimental Analysis of COVID-19 Vaccine Tweets Using BERT+NBSVM

The development of the vaccine for the control of COVID-19 is the need of hour. The immunity against coronavirus highly depends upon the vaccine distribution. Unfortunately, vaccine hesitancy seems to be another big challenge worldwide. Therefore, it is necessary to analysis and figure out the public opinion about COVID-19 vaccines. In this era of social media, people use such platforms and post about their opinion, reviews etc. In this research, we proposed BERT+NBSVM model for the sentimental analysis of COVID-19 vaccines tweets. The polarity of the tweets was found using TextBlob(). The proposed BERT+NBSVM outperformed other models and achieved 73% accuracy, 71% precision, 88% recall and 73% F-measure for classification of positive sentiments while 73% accuracy, 71% precision, 74% recall and 73% F-measure for classification of negative sentiments respectively. Thus, these sentimental and spatial analysis helps in world-wide pandemics by identify the people's attitudes towards the vaccines. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Investigation of cointegration and causal linkages on Bitcoin volatility during COVID-19 pandemic

In this study, we focus on a prominent feature in Bitcoin: its volatility. This paper aims to examine the volatility action of Bitcoin's price during the COVID-19 pandemic through various angles: COVID-19 fear sentiments, investor fear sentiments, macro-financial factors, and crypto market factors. The study utilises daily data from 11 March 2020 to 31 May 2021. We implemented an ARDL bound testing approach to find cointegration, and the Toda-Yamamoto approach to further examine any existing causal relationships between the variables. The empirical results show that COVID-19 fear increased Bitcoin volatility and a unidirectional causal relation was found between them. Investor fear sentiments revealed that US dollar volatility moved in the same direction as Bitcoin volatility, while VIX was found to be insignificant. Gold, crude oil, and the stock market did not influence the volatility of Bitcoin. Overall, only crypto market factors were cointegrated with Bitcoin volatility in the long run. Copyright © 2023 Inderscience Enterprises Ltd.

The relationship between Twitter sentiment and mobility during the COVID-19 pandemic

The COVID-19 pandemic has affected public behavior in a variety of ways. Concerns about the spread of a hitherto unknown virus drove numerous changes in public behavior, including a greater tendency to self-isolate at home. In this study, we assigned numerical scores to key sentiments expressed in COVID-19-related posts on major social media platform Twitter to measure changes in public sentiment during the pandemic. We also examined the relationship between mobility in various locations around Japan and scores for sentiments such as dislike and fear. Our research provided evidence of a tendency for mobility to decline (i.e. for more people to self-isolate at home) roughly one month after scores for negative public sentiment regarding COVID-19 increased. Mobility is closely connected with a variety of economic activities, mainly in service industries. This suggests that the sentiment in Twitter postings on COVID-19 that we discuss in this study is a leading indicator of changes in mobility (the extent to which people self-isolate at home), demonstrating the effectiveness of Twitter data in forecasting short-term changes in economic activity during the pandemic. © 2022 IEEE.

Quantified multidimensional public sentiment characteristics on social media for public opinion management: Evidence from the COVID-19 pandemic.

Background: Public sentiments arising from public opinion communication pose a serious psychological risk to public and interfere the communication of nonpharmacological intervention information during the COVID-19 pandemic. Problems caused by public sentiments need to be timely addressed and resolved to support public opinion management. Objective: This study aims to investigate the quantified multidimensional public sentiments characteristics for helping solve the public sentiments issues and strengthen public opinion management. Methods: This study collected the user interaction data from the Weibo platform, including 73,604 Weibo posts and 1,811,703 Weibo comments. Deep learning based on pretraining model, topics clustering and correlation analysis were used to conduct quantitative analysis on time series characteristics, content-based characteristics and audience response characteristics of public sentiments in public opinion during the pandemic. Results: The research findings were as follows: first, public sentiments erupted after priming, and the time series of public sentiments had window periods. Second, public sentiments were related to public discussion topics. The more negative the audience sentiments were, the more deeply the public participated in public discussions. Third, audience sentiments were independent of Weibo posts and user attributes, the steering role of opinion leaders was invalid in changing audience sentiments. Discussion: Since the COVID-19 pandemic, there has been an increasing demand for public opinion management on social media. Our study on the quantified multidimensional public sentiments characteristics is one of the methodological contributions to reinforce public opinion management from a practical perspective.