Explainable BERT-LSTM Stacking for Sentiment Analysis of COVID-19 Vaccination

Public health surveillance has gained more importance recently due the global COVID-19 pandemic. It is important to track public opinions and positions on social media automatically, so that this information can be used to improve public health. Sentiment analysis and stance detection are two social media analysis methods that can be applied to health-related social media posts for this purpose. In this chapter, the authors perform sentiment analysis and stance detection in Turkish tweets about COVID-19 vaccination. A sentiment- and stance-annotated Turkish tweet dataset about COVID-19 vaccination is created. Different machine learning approaches (SVM and Random Forest) are applied on this dataset, and the results are compared. Widespread COVID-19 vaccination is claimed to be useful in order to cope with this pandemic. Therefore, results of automatic sentiment and stance analysis on Twitter posts on COVID-19 vaccination can help public health professionals during their decision-making processes.

Objective: To make an extensive analysis of sentiment within the discourse surrounding COVID-19 vaccines on Twitter, employing Natural Language Processing (NLP) methodologies. Method: The research methodology encompasses data collection via the Twitter API, followed by sentiment analysis facilitated by the TextBlob library. Pre-processing stages are integrated to cleanse and standardize the Twitter data. Subsequently, sentiment analysis categorizes tweets into positive, negative, and neutral sentiments based on polarity scores. Findings: The findings, grounded in a dataset spanning from March 1, 2022, to April 30, 2022, comprising 61,934 tweets, unveil that 45.0% of tweets conveyed positive sentiment, 17.3% exhibited negativity, and 37.7% maintained neutrality. Moreover, an exploration of tweet subjectivity revealed that 70.1% of the content expressed subjectivity, while 29.9% conveyed objectivity. The research is augmented with visual representations, including word clouds and subjectivity-polarity graphs, that offer a more intuitive understanding of sentiment trends. Novelty: This study contributes to the expanding landscape of sentiment analysis and its application within the context of public health crises, empowering stakeholders with valuable knowledge to enhance vaccine acceptance and effectiveness. The tool used “Tweet Downloader” in data collection makes this study different from other reviewed studies. Keywords: COVID-19 vaccine, Twitter sentiment analysis, Public perception, Natural Language Processing (NLP), Social media data

The COVID-19 pandemic has imposed a public health crisis across the world. The global efforts lead to the development and deployment of multiple vaccines. The success of ending the COVID-19 pandemic relies on the willingness of people to get the vaccines. Social media platforms prove to be a valuable source to perform experiments on sentiment and emotion towards COVID-19 vaccination in many languages, mainly focusing on English. The people express their opinions and emotion on Twitter briefly, which can have tracked almost instantaneously. This helps the governments, public health officials, and decision-makers to understand public opinions towards vaccines. The goal of this research is to investigate public sentiment on COVID-19 vaccines. Twitter social media extracted all Arabic-language tweets mentioning seven vaccines in 7 months from 1 November 2020 to 31 May 2021. A set of Arabic sentiment lexicons were prepared to perform the sentiment analysis. The tweets' monthly average sentiment were calculated from the collected dataset and evaluated comparatively for each vaccine throughout the 11 months. Out of 5.5 million tweets that have been retrieved using the most frequent keywords and hashtags during the COVID-19 pandemic, 202,427 tweets were only considered and included in the monthly sentiment analysis. We considered tweets that mentioned only one vaccine name of the text. The distribution of tweets shows that 47.5% of the considered tweets mentioned the Pfizer vaccine. It is reported that 64% of the total tweets are non-negative while 35% are negative, with a significant difference in sentiment between the months. We observed an increase of non-negative tweets in parallel with increasing negative tweets on May 2021, reflecting the public's rising confidence towards vaccines. Lexicon-based sentiment analysis is valuable and easy to implement the technique. It can be used to track the sentiment regarding COVID-19 vaccines. The analysis of social media data benefits public health authorities by monitoring public opinions, addressing the people's concerns about vaccines, and building the confidence of individuals towards vaccines.

Sentiment analysis is the process of mining the perception of people towards a service, product, policy or imminent issue from textual data. In this project, tweets relevant to Covid-19 Vaccine are extracted utilizing the Tweepy library. Next, tweet texts are converted into usable form in order to do sentiment analysis. After this, SentiWordNet lexicon is used to label the sentiment of the tweets. Stop words removal, Lemmatizing, stemming operations are also applied on the COVID-19 Vaccine tweets text data. Count Vectorizer and Tfidf Vectorizer are applied for mathematical conversion of the preprocessed text. Then, nine classification techniques namely - Multinomial-NB, Bernoulli-NB, Logistic-Regression, Ridge Classifier, Passive-Aggressive-Classifier, Perceptron, Random Forest classifier, AdaBoostClassifier and Linear SVM are applied on the dataset obtained for sentiment classification and results are obtained in terms of accuracy. The best cross validation test score obtained is 0.785 with Logistic Regression Classifier and TfidfVectorizer.

In the realm of contemporary soft computing practices, analysis of public perceptions and opinion mining (OM) have received considerable attention due to the easy availability of colossal data in the form of unstructured text generated by social media, e-commerce portals, blogs, and other similar web resources. The year 2020 witnessed the gravest epidemic in the history of mankind, and in the present year, we stand amidst a global, massive and exhaustive vaccination movement. Since the inception of the COVID-19 vaccines and their applications, people across the globe, from the ordinary public to celebrities and VIPs have been expressing their fears, doubts, experiences, expectations, dilemmas and perceptions about the current COVID-19 vaccination program. Being very popular among a large class of modern human society, the Twitter platform has been chosen in this research to study public perceptions about this global vaccination drive. More than 112 thousand Tweets from users of different countries around the globe are extracted based on hashtags related to the affairs of the COVID-19 vaccine. A three-tier framework is being proposed in which raw Tweets are extracted and cleaned first, visualized and converted into numerical vectors through word embedding and N-gram models next, and finally analyzed through a few machine learning classifiers with the standard performance metrics, accuracy, precision, recall, and F1-measure. The Logistic Regression (LR) and Adaptive Boosting (AdaBoost) classifiers attended the highest accuracies of 87% and 89% with the Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF) word embedding models respectively. Overall, the BoW model achieved slightly better average classification accuracy (78.33%) than that of the TF-IDF model (77.89%). Moreover, the experimental results show that most of the people have a neutral attitude towards the current COVID-19 vaccination drive and people favoring the COVID-19 vaccination program are greater in number than those who doubt it and its consequences.KeywordsVaccineCOVID-19 vaccination programSentiments analysis Twitter Machine learningN-gram

This study aimed to evaluate misinformation surrounding infertility and the COVID-19 vaccine on X (formerly known as Twitter) by analyzing the prevalence and content of this misinformation across a sample of posts on X. This study is a retrospective review of posts on X (formerly known as tweets) from the COVID-19-TweetIDs dataset from July 2021 and November 2021. Included posts were from crucial time points in the COVID-19 vaccine discourse and contained at least one word related to COVID-19 vaccination and fertility. Posts were analyzed and categorized based on factuality, common words, and hashtags. Descriptive statistics on total followers, account verification status, and engagement were obtained. Differences between posts on X classified as factual and misinformation were examined using analysis of variance or χ2 tests. Sentiment analysis determined if post content was generally positive, neutral, or negative. A total of 17,418 relevant posts on X were reviewed: 11,436 from timeframe 1 (July 2021) and 5982 from timeframe 2 (December 2021). Misinformation posts rose from 29.9% in July 2021 to 45.1% in November 2021. In both timeframes, accounts sharing factual information had more followers (p < 0.001), and verified users were more likely to share accurate posts (p ≤ 0.001). Factual and misinformation posts had similar engagement. Sentiment analysis identified that real posts were more positive and misinformation posts were more negative (p < 0.001). Misinformation about the COVID-19 vaccine and fertility is highly prevalent on X and threatens vaccine uptake in patients desiring future fertility. Accounts sharing factual information were likely to have more followers and be verified; therefore, verifying more physicians sharing accurate information is critical.

This study examines the perceptions and results of COVID-19 immunization using sentiment analysis of Twitter data from India. The tweets were collected from January 2021 to March 2023 using relevant hashtags and keywords. The dataset was pre-processed and cleaned before conducting sentiment analysis using Natural Language Processing techniques. Our results show that the overall sentiment toward COVID-19 vaccination in India has been positive, with a majority of tweets expressing support for vaccination and encouraging others to get vaccinated. However, we also identified some negative sentiments related to vaccine hesitancy, side effects, and mistrust in the government and pharmaceutical companies. We further analyzed the sentiment based on demographic factors such as gender, age, and location. The analysis revealed that the sentiment varied across different demographics, with some groups expressing more positive or negative sentiments than others. This study provides insights into the perception and outcomes of COVID-19 vaccination in India and highlights the need for targeted communication strategies to address vaccine hesitancy and increase vaccine uptake in specific demographics.

Social media is one platform where people share their opinions and views on different topics, services, or behaviors that happen around them. Since the COVID19 pandemic that started at the end of 2019, it has been a topic on which people express their sentiments. Recently, the COVID19 vaccination programs have got a lot of responses. In this paper, we have proposed two models: one based on the machine learning approach: Naive Bayes &amp; the other based on deep learning: LSTM, whose goal is to know the sentiment of Asian region tweets towards the vaccine through sentiment analysis. The data were extracted with the help of Twitter API from March 23, 2021, till April 2, 2021. The extraction approach contains keywords with geocoding of some of the Asian countries, especially Nepal, India and Singapore. After collecting data, some preprocessing such as removing numbers, non-English &amp; stop words, removing special characters, and hyperlinks were done. The polarity of tweets was assigned using the Text blob library. The tweets were classified into one of the three: positive, negative, or neutral. Now the data were preprocessed with the splitting of tweets into training &amp; testing sets. Both the models were trained &amp; tested using 10767 unique tweets. This experiment shows that a number of people in these three countries (Nepal, India and Singapore) have positive sentiment towards the vaccine and are taking the first dose of Covid19 vaccine. At last, the accuracy of the LSTM model was found to be 7% greater than that of the Naive Bayes-based model.

Recently Natural Language Processing (NLP) constituted an important area of computational linguistics and artificial intelligence, where the virtual and digital world has become an essential aspect of our daily lives. Sentiment analysis and data mining are sub-fields of NLP, which draw the attention of researchers to search and mine various issues on social media. This study explores the public's sentiments and opinions towards the SARS-CoV-2 vaccination doses in Saudi Arabia. It tries to provide insights on the motivations and barriers in taking the first and second vaccine doses and how the public's awareness and attitudes differ in the two doses. The research objects are 6.232 public tweets and comments that have been harvested from official social media platforms (Twitter and YouTube) between December 19, 2020, and December 10, 2021. The sentiment analysis measured polarity using the NLTK VADER analyzer, and the opinions were identified and classified based on the multidimensional scaling method. The results show that in the case of the first vaccine dose of the 2989 opinions enrolled, 61.5% of the public were willing to take the COVID-19 vaccination—the majority trust the vaccine safety and the Ministry of Health measures and decisions. While 21.1% show negative attitudes towards the vaccination, most of them untrust the vaccine and are worried about its syndromes. In the case of the second vaccine dose of the 3,243 opinions enrolled, 63.2% also show positive attitudes towards taking the vaccine. Trusting the vaccine safety and not being prevented from work, travel, and other activities are the primary motivations to receive the vaccine in this phase. While negative sentiments scored 30.3%, the most frequent determinant is the suspicion of the vaccine safety, symptoms, and decision discrepancies. Identifying public sentiments and attitudes toward COVID-19 vaccination would provide a better understanding of the reasons behind vaccine rejection or acceptance would help the health policymakers better develop and implement vaccine awareness strategies and appropriate communication to enhance vaccine taking.

BackgroundThe COVID-19 pandemic has imposed a large, initially uncontrollable, public health crisis both in the United States and across the world, with experts looking to vaccines as the ultimate mechanism of defense. The development and deployment of COVID-19 vaccines have been rapidly advancing via global efforts. Hence, it is crucial for governments, public health officials, and policy makers to understand public attitudes and opinions towards vaccines, such that effective interventions and educational campaigns can be designed to promote vaccine acceptance.ObjectiveThe aim of this study was to investigate public opinion and perception on COVID-19 vaccines in the United States. We investigated the spatiotemporal trends of public sentiment and emotion towards COVID-19 vaccines and analyzed how such trends relate to popular topics found on Twitter.MethodsWe collected over 300,000 geotagged tweets in the United States from March 1, 2020 to February 28, 2021. We examined the spatiotemporal patterns of public sentiment and emotion over time at both national and state scales and identified 3 phases along the pandemic timeline with sharp changes in public sentiment and emotion. Using sentiment analysis, emotion analysis (with cloud mapping of keywords), and topic modeling, we further identified 11 key events and major topics as the potential drivers to such changes.ResultsAn increasing trend in positive sentiment in conjunction with a decrease in negative sentiment were generally observed in most states, reflecting the rising confidence and anticipation of the public towards vaccines. The overall tendency of the 8 types of emotion implies that the public trusts and anticipates the vaccine. This is accompanied by a mixture of fear, sadness, and anger. Critical social or international events or announcements by political leaders and authorities may have potential impacts on public opinion towards vaccines. These factors help identify underlying themes and validate insights from the analysis.ConclusionsThe analyses of near real-time social media big data benefit public health authorities by enabling them to monitor public attitudes and opinions towards vaccine-related information in a geo-aware manner, address the concerns of vaccine skeptics, and promote the confidence that individuals within a certain region or community have towards vaccines.

Background: Low vaccine acceptance constitutes a major obstacle for achieving herd immunity against coronavirus disease 2019 (COVID-19). Data on COVID-19 show a significant rise in the number of cumulative cases in Arab countries where vaccine uptake is lower than the uptake at the global level for the 2021-2022 period. The aim of this study is to analyze sentiments related to vaccine acceptance before and after the emergence of the COVID-19 Omicron variant in the Arab-speaking world. Methods: Tweets were collected before and after the Omicron emergence period in the Arab-speaking world using Python-enabled CAMeL Tools (Arabic Natural Language Processing toolkit) libraries. A sentiment analysis on COVID-19 vaccines using Arabic hashtags and a sentiment analysis by city were conducted. Results: Two data sets pre-Omicron and post-Omicron tweets exhibited a difference in sentiments marking a shift towards less negativity and more neutrality. Sentiments by city showed most tweets in both periods coming from Riyadh and Jeddah in Saudi-Arabia, and from Salt in Jordan. Conclusions: Despite the limitations of the study, the change in sentiments detected by the study may suggest more vaccine acceptance which raises some hope and perhaps a higher vaccine uptake in the future. The sentiments by city findings may help in the design of future research.

The development of information technology today has experienced very rapid growth. One of the developments in information technology, namely social media such as Twitter, Facebook, and Youtube, are some of the most popular communication media in today's society. Twitter is often used to express emotions about something, either praising or criticizing in the form of emotion. Human emotions can be categorized into five basic emotions, namely love, joy, sadness, anger, and fear. Twitter users' emotional tweets can be known as opinion or sentiment analysis (opinion analysis or sentiment analysis). Sentiment analysis is also carried out to see opinions or tendencies towards a problem or policy, whether they tend to have negative or positive opinions. The COVID-19 vaccine has become one of the discussions with a fairly high intensity on social media. Vaccine-related tweets have increased as government policies evolve. The responses of netizens also varied, ranging from clinical trials of vaccines, free vaccines, vaccine effectiveness, halal vaccines, to the implementation of vaccinations. This research produces a system that can analyze tweet sentiment related to the covid 19 vaccine in Indonesia where the tweet is obtained using the Twitter API. This system uses the Multinominal Naive Bayes method for the classification process.

Procurement of the COVID-19 vaccination has led to diverse opinions among Indonesian people on Twitter. Sentiment analysis on Twitter can be carried out to find out public opinion, especially among Twitter users. The data was used in the form of tweets with the topic of the COVID-19 vaccine using the keywords covid 19 vaccine, covid vaccine, AstraZeneca, Sinovac, Moderna, Pfizer, Novavax and Sinopharm. analysis of the performance of the Naive Bayes Classifier, Support Vector Machine and K-Nearest Neighbors algorithms to determine the results of the accuracy level between the algorithms. The highest classification test is using the Support Vector Machine with an accuracy rate of 0.701. The results of the comparison of algorithms tested using tweet data on the topic of the COVID-19 vaccine found that the Support Vector Machine was better than the Naive Bayes Classifier and K-Nearest Neighbors. From the classification test carried out using COVID-19 vaccine tweet data with 2500 data. The amount of data after going through the data processing process is 1052 data. Neutral sentiment results in as many as 645 positive sentiments as many as 250 and negative sentiments as many as 157.

Social media has emerged as a critical communication tool in contemporary society, bringing the world closer by making news and opinions more accessible through virtual platforms. Among these, Twitter stands out with over 350 million users worldwide. However, the highly unstructured nature of Twitter data poses significant challenges for analysis. Recently, the rich content of social media networks has spurred extensive research, particularly in light of the COVID-19 pandemic that has impacted global populations. Concurrent with the search for a vaccine, numerous studies have focused on analyzing public sentiment during the crisis, using data from various social media platforms. This study concentrates on people's opinions regarding COVID-19 vaccines, employing several machine learning models to analyze data from Twitter. It was discovered that the most accurate algorithm was the SGD Classifier, which utilized all three n-gram ranges, achieving an accuracy of 0.75.

The world is facing the major crisis in the form of coronavirus pandemic. Since it's been more than a year of Covid-19 pandemic, there has been a significant call in social media regarding the requirement and feasibility for COVID-19 Vaccine. This paper aims at analyzing tweets related to Covid-19 Vaccine, determining the sentiments about vaccination and extracting the significant topics. We performed multi-class sentiment analysis, steps comprising of pre-processing followed by training three different classification models: Gaussian Naïve Bayes, Support Vector Machine and LSTM. Results of the model obtained was one the three (Positive, Negative, Neutral) sentiment. Based on the outcomes, accuracy and F1- scores were computed to draw comparison between distinct models. Topic Modeling was performed using LDA on the combined tweets dataset to derive top seven important topics. In addition, Exploratory Data Analysis was also performed on dataset consisting of Vaccination Progress worldwide to bring out popularity of vaccines.