Figure - available from: Sustainability
This content is subject to copyright.
Source publication
It has been more than a year since the coronavirus (COVID-19) engulfed the whole world, disturbing the daily routine, bringing down the economies, and killing two million people across the globe at the time of writing. The pandemic brought the world together to a joint effort to find a cure and work toward developing a vaccine. Much to the anticipa...
Similar publications
Although billions of COVID-19 vaccines have been administered, too many people remain hesitant. Misinformation about the COVID-19 vaccines, propagating on social media, is believed to drive hesitancy towards vaccination. However, exposure to misinformation does not necessarily indicate misinformation adoption. In this paper we describe a novel fram...
The severity of the coronavirus pandemic necessitates the need of effective administrative decisions. Over 4 lakh people in India succumbed to COVID-19, with over 3 crore confirmed cases, and still counting. The threat of a plausible third wave continues to haunt millions. In this ever changing dynamic of the virus, predictive modeling methods can...
Background:
Social media remains a growing platform for physicians to facilitate learning, network, and disseminate information. The Coronavirus Disease 2019 (COVID-19) pandemic has challenged traditional medical student recruitment and outreach. Instagram is a platform that can be used by residency programs to increase engagement and as a potenti...
The spread of coronavirus and anti-vaccine conspiracies online hindered public health responses to the pandemic. We examined the content of external articles shared on Twitter from February to June 2020 to understand how conspiracy theories and fake news competed with legitimate sources of information. Examining external content--articles, rather t...
A growing number of Americans stay informed about current events through social media. But using social media as a source of news is associated with increased likelihood of being misinformed about important topics, such as COVID-19. The two most popular platforms—Facebook and YouTube—remain relatively understudied in comparison to Twitter, which te...
Citations
... LSTM's ability to preserve the previous state allows it to understand the context of words. Therefore, it can outperform DNN and other networks regarding long streams if data Batra et al. (2021). The LSTM network takes the input of the current time step and the output of the previous time step and produces an output fed to the next time step. ...
In March 2020, the whole world suffered from the coronavirus pandemic. This virus is a sort of virus that comes in many forms, some of which may kill. It mainly affects the human respiratory system. The development and search for COVID-19 vaccines became the global goal to stop the spread of the deadly disease. By the end of 2020, the first set of immunizations started to become available. Some countries began their immunization campaigns early. Meanwhile, others awaited the outcome of a successful trial. This research explores classifying users’ hesitation or confidence about COVID-19 immunizations. To determine the sentiment of tweets related to vaccines, we collected tweets in Arabic related to various vaccines. After collecting the tweets, we have done pre-possessing using natural language processing (NLP) techniques. After that, we developed a hybrid approach for data annotation to detect the polarity of data. We used a hybrid data annotation utilizing three different lexicons. Finally, many machine learning (ML) and deep learning (DL) methods such as Multinomial Naïve Bayes (MNB), logistic regression (LR), support vector machine (SVM), long short-term memory (LSTM), combined Gated Recurrent Unit (GRU), conventional neural network and combinations of CNN and LSTM and their hybrid versions were used and compared. Experimental results revealed that the proposed hybrid annotation method outperformed the conventional one in predicting the confidence or hesitation of people regarding COVID-19 vaccines. The maximum accuracy achieved was 98.1% using the hybrid CNN-GRU with a hybrid approach to data annotation.
... Therefore, the COVID-19 pandemic was announced as a threat to the health of all people in the world (2,3). Besides the risk of death, COVID-19 has been associated with numerous health, economic, social, and political consequences for all countries (1,3,4), and public health measures taken to reduce its effects in various countries have brought huge burden and costs on the relevant governments (5). In the mean-time, the vaccine was introduced as a core and effective solution to prevent COVID-19 (2,3). ...
... According to many studies, a large portion of the emotions expressed by users regarding the COVID-19 vaccine on social media has been positive or neutral (4,24,26,28,30,31,33,34,36,37,39,40). Some studies have also demonstrated a higher frequency of negative emotions over positive emotions in users' posts and comments about the COVID-19 vaccine (1,8,29,32). The occurrence of some changes in the emotions expressed by users in posts and comments about the COVID-19 vaccine on social media have been monitored over time as well (1,8,24,25,26,29,31,34,35,39,40). ...
... Some studies have also demonstrated a higher frequency of negative emotions over positive emotions in users' posts and comments about the COVID-19 vaccine (1,8,29,32). The occurrence of some changes in the emotions expressed by users in posts and comments about the COVID-19 vaccine on social media have been monitored over time as well (1,8,24,25,26,29,31,34,35,39,40). ...
Background and Aim: Since the Coronavirus Disease 2019 (COVID-19) pandemic prevailed globally, followed by the provision of its vaccine, social media users worldwide have come to discuss the issue and exchange views accordingly. It seems highly important to understand the nature of the content that users discussing the COVID-19 vaccination regarding the community's general health. Therefore, this systematic review was designed to evaluate the issues and emotions of users on social media regarding the COVID-19 vaccine.Material and Methods: The research data of this systematic review were extracted from the onset of the COVID-19 until November 20, 2021, by employing a proper search strategy in PubMed, Scopus, and Web of Science databases. The original research articles published in English consistent with the study objective were considered the research inclusion criteria. The authors excluded all short articles, letters to the editor, conference proceeding, review articles, and papers whose full texts were not available.Results: The results revealed that most of the users' expressed emotions about the vaccine on social media were positive or neutral, and there were few negative emotions. The most frequent topics in posts and comments shared by social media users included safety and effectiveness, vaccine development and its speed, prevention policies, and health and political authorities.Conclusion: Nowadays, social media can help understand attitudes and behaviors during a public health crisis and promote health messages. Accordingly, it appears crucial to get aware of people's perspectives on social media platforms to assist in designing communication strategies for health policymakers.
... Although initially, deep learning made inroads in image and video processing, however, later in the years, due to improvements in recurrent neural network (RNN) and long short-term memory (LSTM) network, natural language processing tasks were also equally benefited. NLP tasks like sentiment analysis [23][24][25][26][27][28], document classification [29][30][31][32][33][34], topic modelling [35][36][37][38], seq2seq generation [39,40], etc., are now best suited to deep neural networks and their different variations. ...
The Internet revolution has resulted in abundant data from various sources, including social media, traditional media, etcetera. Although the availability of data is no longer an issue, data labelling for exploiting it in supervised machine learning is still an expensive process and involves tedious human efforts. The overall purpose of this study is to propose a strategy to automatically label the unlabeled textual data with the support of active learning in combination with deep learning. More specifically, this study assesses the performance of different active learning strategies in automatic labelling of the textual dataset at sentence and document levels. To achieve this objective, different experiments have been performed on the publicly available dataset. In first set of experiments, we randomly choose a subset of instances from training dataset and train a deep neural network to assess performance on test set. In the second set of experiments, we replace the random selection with different active learning strategies to choose a subset of the training dataset to train the same model and reassess its performance on test set. The experimental results suggest that different active learning strategies yield performance improvement of 7% on document level datasets and 3% on sentence level datasets for auto labelling.
... In this sense, this social network can be useful to investigate the public discourse related to these two crises that impacted the course of the pandemic, the AstraZeneca-related thrombus cases, and the circulation of the new omicron variant. There are many studies that have investigated the public discourse about COVID-19 vaccines on Twitter [23][24][25][26], but few of them did so specifically on these two specific crises. Marcec and Likic [27], for example, have investigated sentiments towards AstraZeneca/Oxford, Pfizer/BioNTech, and Moderna vaccines on English posts on Twitter and Jemielniak and Krempovych [17], related to misinformation and fear about the AstraZeneca vaccine also on this same social network. ...
Social media have been the arena of different types of discourse during the COVID-19 pandemic. We aim to characterize public discourse during health crises in different international communities. Using Tweetpy and keywords related to the research, we collected 3,748,302 posts from the English, French, Portuguese, and Spanish Twitter communities related to two crises during the pandemic: (a) the AstraZeneca COVID-19 vaccine, and (b) the Omicron variant. In relation to AstraZeneca, ‘blood clot’ was the main focus of public discourse. Using quantitative classifications and natural language processing algorithms, results are obtained for each language. The English and French discourse focused more on “death”, and the most negative sentiment was generated by the French community. The Portuguese discourse was the only one to make a direct reference to a politician, the former Brazilian President Bolsonaro. In the Omicron crisis, the public discourse mainly focused on infection cases follow-up and the number of deaths, showing a closer public discourse to the actual risk. The public discourse during health crises might lead to different behaviours. While public discourse on AstraZeneca might contribute as a barrier for preventive measures by increasing vaccine hesitancy, the Omicron discourse could lead to more preventive behaviours by the public, such as the use of masks. This paper broadens the scope of crisis communication by revealing social media’s role in the constructs of public discourse.
... In recent years, SA has become a strong tool for tracking and understating users' opinions. In 2020, with the start of the pandemic, social media platforms, particularly Twitter played an essential role as communication channels to share people's reactions to coronavirus (covid-19) lockdown [2], [3], healthcare services [4], vaccination [5], [6], etc. ...
Energy prices have gone up gradually since last year, but a drastic hike has been observed recently in the past couple of months, affecting people’s thrift. This, coupled with the load shedding and energy shortages in some parts of the world, led many to show anger and bitterness on the streets and on social media. Despite subsidies offered by many Governments to their citizens to compensate for high energy bills, the energy price hike is a trending topic on Twitter. However, not much attention is paid to opinion mining on social media posts on this topic. Therefore, in this study, we propose a solution that takes advantage of both a transformer-based sentiment analysis method and topic modeling to explore public engagement on Twitter regarding energy prices rising. The former method is employed to annotate the valence of the collected tweets as positive, neutral and negative, whereas the latter is used to discover hidden topics/themes related to energy prices for which people have expressed positive or negative sentiments. The proposed solution is tested on a dataset composed of 366,031 tweets collected from 01 January 2021 to 18 June 2022. The findings show that people have discussed a variety of topics which directly or indirectly affect energy prices. Moreover, the findings reveal that the public sentiment towards these topics has changed over time, in particular, in 2022 when negative sentiment was dominant.
... As directions for further research, we highlight: (1) improvement of the technical data scraping process to extract more significant amounts of geocoded tweets about the desired topic; (2) development of an improved process for manual annotation on the opinion polarities, also considering labels referring to emotions such as happiness, anger, anguish, anxiety, fear, sadness, surprise, etc. Additionally, we highlight [75] for new space and time analyses; (3) testing and comparing the performance of other topic modeling algorithms specifically designed to work with short texts; (4) combining prospects of social distancing and mobility restrictions in different categories within the geographical locations [76]; and (5) analysis from the perspective of the psychological effects of public discussion on the social web on how the individual develops his opinion on the immunization programs. ...
The context of the COVID-19 pandemic has brought to light the infodemic phenomenon and the problem of misinformation. Agencies involved in managing COVID-19 immunization programs are also looking for ways to combat this problem, demanding analytical tools specialized in identifying patterns of misinformation and understanding how they have evolved in time and space to demonstrate their effects on public trust. The aim of this article is to present the results of a study applying topic analysis in space and time with respect to public opinion on the Brazilian COVID-19 immunization program. The analytical process involves applying topic discovery to tweets with geoinformation extracted from the COVID-19 vaccination theme. After extracting the topics, they were submitted to manual annotation, whereby the polarity labels pro, anti, and neutral were applied based on the support and trust in the COVID-19 vaccination. A space and time analysis was carried out using the topic and polarity distributions, making it possible to understand moments during which the most significant quantities of posts occurred and the cities that generated the most tweets. The analytical process describes a framework capable of meeting the needs of agencies for tools, providing indications of how misinformation has evolved and where its dissemination focuses, in addition to defining the granularity of this information according to what managers define as adequate. The following research outcomes can be highlighted. (1) We identified a specific date containing a peak that stands out among the other dates, indicating an event that mobilized public opinion about COVID-19 vaccination. (2) We extracted 23 topics, enabling the manual polarity annotation of each topic and an understanding of which polarities were associated with tweets. (3) Based on the association between polarities, topics, and tweets, it was possible to identify the Brazilian cities that produced the majority of tweets for each polarity and the amount distribution of tweets relative to cities populations.
... Such a study is conducted in [24], where the authors proposed a classification approach for emotion detection from text using deep neural networks including Bi-LSTM, and CNN, with self-attention and three pre-trained word-embeddings for words encoding. Another similar example where LSTM models are used for estimating the sentiment polarity and emotions from Covid-19 related tweets is proposed in [10] and in [2]. The later study also introduced a new approach employing emoticons as a unique and novel way to validate deep learning models on tweets extracted from Twitter. ...
Automatic text-based sentiment analysis and emotion detection on social media platforms has gained tremendous popularity recently due to its widespread application reach, despite the unavailability of a massive amount of labeled datasets. With social media platforms in the limelight in recent years, it’s easier for people to express their opinions and reach a larger target audience via Twitter and Facebook. Large tweet postings provide researchers with much data to train deep learning models for analysis and predictions for various applications. However, deep learning-based supervised learning is data-hungry and relies heavily on abundant labeled data, which remains a challenge. To address this issue, we have created a large-scale labeled emotion dataset of 1.83 million tweets by harnessing emotion-indicative emojis available in tweets. We conducted a set of experiments on our distant-supervised labeled dataset using conventional machine learning and deep learning models for estimating sentiment polarity and multi-class emotion detection. Our experimental results revealed that deep neural networks such as BiLSTM and CNN-BiLSTM outperform other models in both sentiment polarity and multi-class emotion classification tasks achieving an F1 score of 62.21% and 39.46%, respectively, an average performance improvement of nearly 2–3 percentage points on the baseline results.KeywordsSentiment polarityEmotion detectionDistant supervisionEmojiDeep learningTwitterClassification
... An opinion analysis framework can describe the process applied in this work based on other analytical processes proposed in the literature (see, for instance, [20][21][22][23]). Essentially, a framework or analytical process for sentiment or opinion analysis has to deal with [24,25]: The framework implemented and applied in our research contains all these steps, but it adds one more item: the temporal opinion analysis. ...
... We were able to demonstrate a process for identifying potential events related to peaks in the number of messages containing polarized opinions about the vaccination campaign against COVID-19 in Brazil, following premises we observed in previous studies [20][21][22]58] and opening space for continuities by applying other techniques capable of further filtering useful information by collecting messages from social network users. The analytical process we applied demonstrates that it is possible to generate mechanisms for automating searches for news of benign or harmful events to verify if they were the focus of misinformation or fake news [5,59]. ...
This article presents a study that applied opinion analysis about COVID-19 immunization in Brazil. An initial set of 143,615 tweets was collected containing 49,477 pro- and 44,643 anti-vaccination and 49,495 neutral posts. Supervised classifiers (multinomial naïve Bayes, logistic regression, linear support vector machines, random forests, adaptative boosting, and multilayer perceptron) were tested, and multinomial naïve Bayes, which had the best trade-off between overfitting and correctness, was selected to classify a second set containing 221,884 unclassified tweets. A timeline with the classified tweets was constructed, helping to identify dates with peaks in each polarity and search for events that may have caused the peaks, providing methodological assistance in combating sources of misinformation linked to the spread of anti-vaccination opinion.
... For example, Villavicencio et al. (2021) used English and Filipino tweets to get public opinions on vaccination in the Philippines, while Nurdeni, Budi, and Santoso conducted a similar study in Indonesia using English tweets. Another study by Batra et al. (2021) evaluated sentiments in India, the USA, Norway, and Pakistan using English tweets. However, there are no studies that have been done in Arabic countries, or using Arabic tweets, in order to highlight how people in such countries perceive the COVID-19 vaccines. ...
... Various analytical methods were used, but the BERT model and Naïve Bayes gave the highest accuracy of 84% and 81%, respectively. Another research by Batra et al. (2021) collected tweets from Norway, India, Pakistan, the USA, Sweden, and Canada to evaluate the cross-cultural emotions towards the COVID-19 vaccine. The classification models that were used in the study were Deep Neural Network (DNN), Long Short Term Memory (LSTM) Network, and the Convolution Neural Network (CNN). ...
IntroductionThe development of COVID-19 vaccines has been a great relief in many countries that have been affected by the pandemic. As a result, many governments have made significant efforts to purchase and administer vaccines to their populations. However, accommodating such vaccines is typically confronted with people’s reluctance and fear. Like any other important event, COVID-19 vaccines have attracted people’s discussions on social media and impacted their opinions about vaccination.Objective
The goal of this study is twofold: First, it conducts a sentiment analysis around COVID-19 vaccines by automatically analyzing Arabic users’ tweets. This analysis has been spread over time to better capture the changes in vaccine perceptions. This will provide us with some insights into the most popular and accepted vaccine(s) in the Arab countries, as well as the reasons behind people’s reluctance to take the vaccine. Second, it develops models to detect any vaccine-related tweets, to help with gathering all information related to people’s perception of the virus, and potentially detecting vaccine-related tweets that are not necessarily tagged with the virus’s main hashtags.Methods
Arabic Tweets were collected by the authors, starting from January 1st, 2021, until April 20th, 2021. We deployed various Natural Language Processing (NLP) to distill our selected tweets. The curated dataset included in the analysis consisted of 1,098,376 unique tweets. To achieve the first goal, we designed state-of-the-art sentiment analysis techniques to extract knowledge related to the degree of acceptance of all existing vaccines and what are the main obstacles preventing the wide audience from accepting them. To achieve the second goal, we tackle the detection of vaccine-related tweets as a binary classification problem, where various Machine Learning (ML) models were designed to identify such tweets regardless of whether they use the vaccine hashtags or not.ResultsGenerally, we found that the highest positive sentiments were registered for Pfizer-BioNTech, followed by Sinopharm-BIBP and Oxford-AstraZeneca. In addition, we found that 38% of the overall tweets showed negative sentiment, and only 12% had a positive sentiment. It is important to note that the majority of the sentiments vary between neutral and negative, showing the lack of conviction of the importance of vaccination among the large majority of tweeters. This paper extracts the top concerns raised by the tweets and advocates for taking them into account when advertising for the vaccination. Regarding the identification of vaccine-related tweets, the Logistic Regression model scored the highest accuracy of 0.82. Our findings are concluded with implications for public health authorities and the scholarly community to take into account to improve the vaccine’s acceptance.
... OM refers to the current trend used in text mining, information retrieval, and computational Linguistics, trying to identify the opinions expressed in natural language text" [14]. The basic motivation for opinion mining is to extract ideas, opinions and opinions from user suggestions and present the information in an efficient way [15]. Unlike user experiences for various products, tools and technologies from end users [16], consumers usually present their opinions in the form of review sentences containing a single word or phrase [17]. ...
Discovering what other people think has always been a key aspect of our information-gathering strategy. People can now actively utilize information technology to seek out and comprehend the ideas of others, thanks to the increased availability and popularity of opinion-rich resources such as online review sites and personal blogs. Because of its crucial function in understanding people's opinions, sentiment analysis (SA) is a crucial task. Existing research, on the other hand, is primarily focused on the English language, with just a small amount of study devoted to low-resource languages. For sentiment analysis, this work presented a new multi-class Urdu dataset based on user evaluations. The tweeter website was used to get Urdu dataset. Our proposed dataset includes 10,000 reviews that have been carefully classified into two categories by human experts: positive, negative. The primary purpose of this research is to construct a manually annotated dataset for Urdu sentiment analysis and to establish the baseline result. Five different lexicon- and rule-based algorithms including Naivebayes, Stanza, Textblob, Vader, and Flair are employed and the experimental results show that Flair with an accuracy of 70% outperforms other tested algorithms.
