Analysis of Public Sentiment on COVID-19 Vaccination Using Twitter

<p>In March of 2020, the World Health Organization identified COVID-19 as a new pandemic and issued a statement to that effect. This fatal virus was able to disperse and propagate throughout several countries all over the world. During the progression of the pandemic, social networking sites like Twitter generated significant and substantial volumes of data that helped improve the quality of decisions pertaining to health care applications. In this paper, we proposed a sentiment classification using various feature extraction and machine leavening techniques for social media dataset. The system has divided into four phase data collection, preprocessing and normalization, feature extraction and feature selection and finally classification. In first phase we collect data from social media sources such as twitter using Twitter API. In second phase the tweets, data was ready for preprocessing and it was sorted into three categories: positive, neutral, and negative. During the third phase, various features were extracted from the tweets by employing a number of widely utilized approaches, including as bag of words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, and FastText, to gather feature datasets. These methods were employed to extract distinct datasets for the features. The final phase different machine learning classification algorithms are applied for detection of sentiment using machine learning. In the extensive experimental analysis, the BoW performed better results with modified support vector machine (mSVM) than existing machine learning algorithms. The proposed mSVM performed superiorly to the other classifiers by 98.15% accuracy rate. Once the tweets are correctly classified as COVID-19 tweets, it is further categorized into three sentiments that is positive, negative and neural. Proposed mSVM achieves 93% of accuracy rate for positive sentiment which better as compared to other Machine Learning (ML) classifiers.</p>

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

Sentiment analysis, which stands for opinion mining, is a natural language processing (NLP) technique that involves identifying, extracting, and analyzing sentiments or opinions expressed in text data. The primary goal of sentiment analysis is to determine the sentiment polarity of a given piece of text, whether it is positive, negative, or neutral. This analysis can be applied to various types of content, such as product reviews, social media posts, customer feedback, and news articles. Sentiment analysis algorithms use machine learning and text classification to understand subjective information conveyed in text, helping businesses, organizations, and individuals gain insight into public opinions and emotions about specific topics, products, or services. In this study, we conducted sentiment analysis on a Bengali dataset. For feature extraction, we implemented the term frequency-inverse document frequency (TF-IDF) technique, and for feature selection, we applied an extra tree classifier approach. Subsequently, we trained our machine learning model, achieving an impressive accuracy rate of 92%.

BACKGROUNDIn the Spring of 2020, residency programs across the country experienced rapid and drastic changes to their application process as a result of the coronavirus disease 2019 (COVID-19) pandemic. In response, residency programs shifted to virtual events and began harnessing social media to communicate with applicants.AIMTo analyze the changes in social media usage by orthopaedic surgery programs in response to the COVID-19 pandemic.METHODSBased on the 2019 residency and fellowship electronic database, accredited US orthopaedic surgery programs were reviewed for social media presence on Instagram and Twitter. Approximately 47000 tweets from 2011-2021 were extracted through the Twitter application programming interface. We extracted: Total number of followers, accounts following, tweets, likes, date of account creation, hashtags, and mentions. Natural language processing was utilized for tweet sentiment analysis and classified as positive, neutral, or negative. Instagram data was collected and deemed current as of August 11, 2021. The account foundation date analysis was based on the date recognized as the start of the COVID-19 outbreak in the United States, before or after March 1, 2020.RESULTSA total of 85 (42.3%) orthopaedic surgery residency program Twitter handles were identified. Thirty-five (41.2%) programs joined Twitter in the nine months after the 2020 covid outbreak. In 2020, there was a 126.6% increase in volume of tweets by orthopaedic surgery residency accounts as compared to 2019. The median number of followers was 474.5 (interquartile range 205.0-796.5). The account with the highest number of tweets was Hospital for Special Surgery (@HSpecialSurgery) with 13776 tweets followed by University of Virginia (@UVA_Ortho) with 5063 and Yale (@OrthoAtYale) with 899. Sentiment analysis before 2020 revealed 30.4% positive, 60.8% neutral, and 8.8% negative sentiments across tweets. Interestingly, the positive sentiment percentage increased in 2020 from 30.4% to 34.5%. Of the 201 ACGME-accredited orthopaedic residency programs on Fellowship and Residency Electronic Interactive Database, 115 (57.2%) participate on Instagram, with 101 (87.8%) identified as “resident”-managed vs 14 (12.2%) identified as “department”-managed. Over three quarters (77.4%) of Instagram accounts were created after March 1, 2020. The average number of followers per account was 1089.5 with an average of 58.9 total posts. CONCLUSIONOur study demonstrates a substantial growth of Instagram and Twitter presence by orthopaedic surgery residency programs during the COVID-19 pandemic. These data suggest that orthopaedic residency programs have utilized social media as a new way to communicate with applicants and showcase their programs in light of the challenges presented by the pandemic.

Social media platforms, particularly Twitter, generate vast volumes of user-generated content that reflect real-time human emotions and opinions. Emotion analysis of such data offers significant value in areas including mental health monitoring, public sentiment tracking, and opinion mining. In this paper, we present a machine learning-based approach for automatically classifying emotions expressed in tweets into six distinct categories: joy, sadness, anger, fear, love, and surprise. The proposed system employs Natural Language Processing (NLP) techniques for text preprocessing, including tokenization, stopword removal, and lemmatization using the NLTK library. Feature extraction is performed using the Term Frequency-Inverse Document Frequency (TF-IDF) vectorization method with unigram and bigram representations. Three supervised machine learning algorithms are evaluated — Logistic Regression, Multinomial Naive Bayes, and Linear Support Vector Machine (LinearSVC) — and compared based on accuracy, precision, recall, and F1-score metrics. Experiments are conducted on the publicly available dairai/emotion dataset comprising over 20,000 labeled tweets. Results demonstrate that Logistic Regression with TF-IDF achieves the highest classification accuracy, outperforming the other models. The study confirms that classical machine learning models, when combined with effective text preprocessing and feature engineering, provide a reliable and computationally efficient framework for multi-class emotion detection in short social media text.

IntroductionSince the Coronavirus disease 2019 (COVID-19), public safety measures, including social distancing and school closures, have been implemented, precipitating psychological difficulties and heightened online activities for adolescents. However, studies examining the impact of the pandemic on adolescent mental health and their coping strategies in Asian countries are limited. Further, most studies have used survey measures to capture mental health challenges so far. Accordingly, this study aimed to examine the psychological challenges South Korean adolescents experienced and their coping strategies during the pandemic using the Natural Language Processing (NLP) and Text mining (TM) technique on adolescents’ social media texts/posts.MethodsThe data were gathered from social media texts/posts such as online communities, Twitter, and personal blogs from January 1, 2019, to October 31, 2021. The 12,520,250 texts containing keywords related to adolescents’ common psychological difficulties reported during the pandemic, including self-harm, Attention-Deficit/Hyperactivity Disorders (ADHD), and insomnia, were analyzed by TM, NLP using information extraction, co-occurrence and sentiment analysis. The monthly frequency of the keywords and their associated words was also analyzed to understand the time trend.ResultsAdolescents used the word “self-harm” in their social media texts more frequently during the second wave of COVID-19 (August to September 2020). “Friends” was the most associated word with “self-harm.” While the frequency of texts with “Insomnia” stayed constant throughout the pandemic, the word “ADHD” was increasingly mentioned in social media. ADHD and insomnia were most frequently associated with ADHD medications and sleeping pills, respectively. Friends were generally associated with positive words, while parents were associated with negative words.ConclusionDuring COVID-19, Korean adolescents often expressed their psychological challenges on social media platforms. However, their coping strategies seemed less efficient to help with their difficulties, warranting strategies to support them in the prolonged pandemic era. For example, Korean adolescents shared psychological challenges such as self-harm with friends rather than their parents. They considered using medicine (e.g., sleeping pills and ADHD medication) as coping strategies for sleep and attention problems.

Social media are the influential Internet community for general netizens to disseminate information, views, and opinions extensively. Recently, the research on Sentiment analysis has intensified due to the vast amount of data obtained from these numerous social networking platforms. During this COVID-19 pandemic, one of the great social networking sites viz. Twitter has experienced a significant increase in online posts and reviews concerning COVID-19 related tweets. In the view of Twitter, the spread of news concerning coronavirus variants has impacted many aspects of the public by providing messages around different issues and opinions to its potential users. In this study, we have used Twitter as a source of data for searching the index keywords and hashtag versions for the terms like “Pandemic”, “Coronavirus”, “COVID-19”, “SARS-CoV-2”, and “Omicron”, and we have examined the psychological and emotional impact it had on the public. This paper provides analytical information about people’s perceptions of coronavirus (tweets were collected from March 2020 to December 2021). With those tweets, sentiment analysis was performed using the TextBlob text processing python module to acquire the people’s subjective data (opinions and feelings) polarity concerning the effects of coronavirus. Furthermore, for effective text classification, we have applied classification methodologies like Support Vector Machine (SVM), K Nearest Neighbor (KNN), Logistic Regression (LR), and Decision Tree (DT). The SVM concerning feature extraction produced the results with 99.49% accuracy. This study assists the government organizations in attaining COVID-19 insights by implying public mental health sentiments in social networks.

The proliferation of fake news across online media platforms poses significant challenges to public trust,societal harmony,and information integrity.Many of the things that people read online, particularly on social media, seem true, but they are frequently not. Fake news is defined as news, articles, or hoaxes that are purposefully created to mislead or deceive readers..This study develops a machine learning-based system for detecting fake news on digital platforms. Utilizing algorithms such as K-Nearest Neighbors (KNN), Naive Bayes, Logistic Regression, Random Forest, Gradient Boosting and Support Vector Machines (SVM), the system processes textual data using natural language processing (NLP) techniques like term frequency-inverse document frequency (TF-IDF) and bag-of- words for feature extraction.The performance of each algorithm is evaluated using metrics such as accuracy, precision, recall, and F1-score to identify the most effective model. By identifying the most effective machine learning model, this research aims to provide a scalable solution that can help reduce misinformation and enhance the credibility of online information.By distinguishing the best A1 model,this expectation expects to give a versatile arrangement that can assist with lessening deception and improve the believability of online data. Keywords- News and Fake,Natural Language Processing,Feature Extraction,a classification and Model Evaluation

We can state undoubtedly that Bangla language is rich enough to work with and implement various Natural Language Processing (NLP) tasks. Though it needs proper attention, hardly NLP field has been explored with it. In this age of digitalization, large amount of Bangla news contents are generated in online platforms. Some of the contents are inappropriate for the children or aged people. With the motivation to filter out news contents easily, the aim of this work is to perform document level sentiment analysis (SA) on Bangla online news. In this respect, the dataset is created by collecting news from online Bangla newspaper archive. Further, the documents are manually annotated into positive and negative classes. Composite process technique of “Pipeline” class including Count Vectorizer, transformer (TF-IDF) and machine learning (ML) classifiers are employed to extract features and to train the dataset. Six supervised ML classifiers (i.e. Multinomial Naive Bayes (MNB), K-Nearest Neighbor (K-NN), Random Forest (RF), (C4.5) Decision Tree (DT), Logistic Regression (LR) and Linear Support Vector Machine (LSVM)) are used to analyze the best classifier for the proposed model. There has been very few works on SA of Bangla news. So, this work is a small attempt to contribute in this field. This model showed remarkable efficiency through better results in both the validation process of percentage split method and 10-fold cross validation. Among all six classifiers, RF has outperformed others by 99% accuracy. Even though LSVM has shown lowest accuracy of 80%, it is also considered as good output. However, this work has also exhibited surpassing outcome for recent and critical Bangla news indicating proper feature extraction to build up the model.

Background: Text classification techniques are increasingly important with the exponential growth of textual data on the internet. Term Frequency-Inverse Document Frequency (TF-IDF) and Count Vectorizer(CV) are commonly used methods for feature extraction. TF-IDF assigning weights to terms based on their frequency. CV simply counts the occurrences of terms. The performance of CV as well as TF-IDF are evaluated and compared with KNN and DT classifiers across text datasets. Methodology: The investigation begins with preprocessing. The feature vectors are created using both TF-IDF and CV. Feature vectors are passed into the KNN and DT classifiers at in training stage. Experiments are executed the usage of Kaggle's public database Ukraine 10K tweets sentiment_analysis dataset and the Womens ecommerce clothing reviews dataset. Findings: The average of precision, recall, f1 score and accuracy of KNN with TF-IDF were 84.5%, 87%, 83%, 87% respectively and KNN with CV were 83.5%, 87%, 83.5%, 87% respectively. Similarly, average of precision, recall, f1 score and accuracy of DT with TF-IDF were 89%, 89%, 89%, 89% respectively and DT with CV were 89%, 89.5%, 89.5%, 89.5% respectively. The results obtained in this research is consistent with previous similar research result. Conclusions: The performance of TF-IDF is almost similar as CV for a particular dataset and a particular classifier in this study. Novelty: The experiment performed using these classifiers and feature extraction methods on the datasets is a novelty and contribution of this research.

Sentiment analysis, a crucial aspect of Natural Language Processing (NLP), plays a pivotal role in understanding public opinion, customer feedback, and user sentiments in various domains. In this study, we present a comprehensive approach to sentiment analysis that incorporates both textual and emoji data, leveraging diverse datasets from sources such as social media, customer reviews, and surveys. Our methodology consists of several key steps, including data collection, pre-processing, feature extraction, feature fusion, and feature selection. For data pre-processing, we apply techniques such as tokenization, lowercasing, stop word removal, and stemming to ensure uniform and meaningful text representation. We also extract emojis from text using regular expressions and convert them into textual representations, facilitating unified processing. Text data is transformed into feature vectors using Term frequency_ Inverse Term frequency (TF-IDF) weighting-based Bag of Words (TF-IDF_BoW) with word frequencies, pre-trained Word2Vec word embeddings, and n-grams to capture local word patterns. Emoji data, on the other hand, is processed using pre-trained emoji embeddings (Emoji2Vec) and emoji frequency counting. The Feature Fusion stage involves the combination of text and emoji features into a single feature vector, with a weighted concatenation approach. In the Feature Selection phase, introduced a Self-Improved Siberian Tiger Optimization (SI-STO), a novel feature selection technique, to identify the most relevant features for sentiment prediction. The sentiment classification model SentEmoNet combines LSTM with an Attention Mechanism and a CNN for capturing text patterns and extracting local features from text and emoji embeddings. We use standard sentiment analysis metrics to assess performance in the model evaluation phase. The proposed model has achieved an accuracy of 97.87%, which is better than the existing ones.

PurposeThe purpose of this paper is to analyze topics as alternative features for sentiment analysis in Indonesian tweets.Design/methodology/approachGiven Indonesian tweets, the processes of sentiment analysis start by extracting features from the tweets. The features are words or topics. The authors use non-negative matrix factorization to extract the topics and apply a support vector machine to classify the tweets into its sentiment class.FindingsThe authors analyze the accuracy using the two-class and three-class sentiment analysis data sets. Both data sets are about sentiments of candidates for Indonesian presidential election. The experiments show that the standard word features give better accuracies than the topics features for the two-class sentiment analysis. Moreover, the topic features can slightly improve the accuracy of the standard word features. The topic features can also improve the accuracy of the standard word features for the three-class sentiment analysis.Originality/valueThe standard textual data representation for sentiment analysis using machine learning is bag of word and its extensions mainly created by natural language processing. This paper applies topics as novel features for the machine learning-based sentiment analysis in Indonesian tweets.

In December 2019, a highly contagious disease, Coronavirus disease 2019 (COVID-19) was first detected in Wuhan, China. The disease has spread to 212 countries and territories worldwide. While this epidemic has continued to infect millions of people, several nations have resorted to complete lockdowns. People took social networks during this shutdown to share their opinions, feelings, and find a way to calm down. This study proposed a US-based sentiment analysis of the tweets using machine learning and the lexicon analysis approach. This US-based tweets dataset was collected by RStudio software from 30 January 2020 to 10th May 2020, contains 11858 tweets. We find the label corresponding to each tweet using TextBlob, that is to say, positive, negative, or neutral. To clean up the facts we pre-process the tweets. In a later step, different feature techniques such as bag-of-words (BoW) and term frequency-inverse document frequency (TF-IDF) are used to preserve expressive information. Finally, the random forest, gradient boosting machine, extra tree classifier, logistic regression, and support vector machine models are used to categorize beliefs as being positive, negative, or neutral. Our suggested pipeline output is assessed using accuracy, precision, recall & F <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</inf> score. This research study shows how TF-IDF features can increase the performance of the supervised machine learning models and in this work, the gradient boosting machine outperforms the others and achieves high accuracy of 96% when paired with TF-IDF features. This analysis was done to analyze how the situation is being handled by citizens of the United States. The results of the experiments validate the approach’s effectiveness.

Natural Language Processing (NLP) is a revolutionary discipline that resides at the crossroads of computer science and linguistics, with its primary emphasis on the interaction between computers and human language. With roots in artificial intelligence, NLP seeks to equip machines with the ability to comprehend, interpret, and respond to natural language, enabling more intuitive and meaningful communication between humans and computers. This multidisciplinary domain leverages advanced algorithms and models to tackle a range of linguistic challenges, from language translation and sentiment analysis to speech recognition. Recent breakthroughs, particularly in deep learning and neural networks, have propelled NLP to new heights, with applications spanning diverse sectors such as healthcare, finance, and education. As NLP continues to advance, its potential impact on enhancing human-machine interaction and information processing is increasingly evident, promising a future where technology seamlessly integrates with our natural modes of communication. The significance of Natural Language Processing (NLP) in research lies in its capacity to revolutionize human-computer interaction. NLP empowers machines to understand and generate human language, enabling advancements in sentiment analysis, language translation, and conversational AI. This transformative capability has profound implications across various industries, including healthcare, finance, and education. NLP research not only enhances the efficiency of information retrieval and processing but also holds the key to developing more intuitive and user-friendly technologies. As the frontier of NLP research expands, its potential to bridge the communication gap between humans and machines continues to shape the future of technology and information access. VIKOR functions as a multi-criteria decision-making technique that determines the best option by comparing it to the ideal option. The ranking procedure comprises determining distances concerning the optimal solution. VIKOR uses linear normalization to get the best possible outcomes. This technique was first presented by Opricovic in 1998 and was intended to optimize multi-attribute complex systems. Its main focus is on ranking lists that allow for flexibility in the strategy weight interval and incorporate compromise alternatives to obtain desired results. Alternative taken as Open AI GPT-4, Google BERT, Microsoft Azure Text Analytics, IBM Watson Natural Language Understanding, spaCy, NLTK (Natural Language Toolkit), Amazon Comprehend. Evaluation Parameter taken as Sentiment Analysis (F1 Score), NER Performance, Language Support, Processing Speed (Response Time) (ms), Translation Accuracy (BLEU Score), Data Privacy. The result it is seen that Amazon Comprehend is got the first rank where as is the IBM Watson Natural Language Understanding is having the lowest rank.

Sentiment analysis is a method that allows us to analyze and understand the feelings and opinions expressed by people. This study focused on the sentiment exhibited by students in their feedback, reviews, and narratives to gain insights into their educational experiences. Our study aims to discern the emotional nuances and attitudes prevalent among students leveraging cutting-edge natural language processing (NLP) techniques through the analysis of textual data collected from various educational settings. This study also seeks to identify positive and negative sentiments. The research methodology entails gathering relevant data expressed on social media platforms such as the “X” platform, and then preprocessing was performed on the data to reduce noise, standardize formats, and prepare it for sentiment analysis. We applied machine learning techniques support vector machine (SVM), logistic regression (LR), K-nearest neighbors (KNN), and XGBoost (XGB) with term frequency-inverse document frequency (TF-IDF) and N-gram to extract the features and compare the results. Our results show that LR obtained the highest accuracy of 94%. The results of this study may help educational institutions in making appropriate decisions to improve and develop the quality of education. Received: May 3, 2024Accepted: June 1, 2024