Popular social media platforms, such as Twitter, have become an excellent source of information with their swift information dissemination. Individuals with different backgrounds convey their opinions through social media platforms. Consequently, these platforms have become a profound instrument for collecting enormous datasets. We believe that compiling, organizing, exploring, and analyzing data from social media platforms, such as Twitter, can offer various perspectives to public health organizations and decision makers in identifying factors that contribute to vaccine hesitancy. In this study, public tweets were downloaded daily from Tweeter using the Tweeter API. Before performing computation, the tweets were preprocessed and labeled. Vocabulary normalization was based on stemming and lemmatization. The NRCLexicon technique was deployed to convert the tweets into ten classes: positive sentiment, negative sentiment, and eight basic emotions (joy, trust, fear, surprise, anticipation, anger, disgust, and sadness). t-test was used to check the statistical significance of the relationships among the basic emotions. Our analysis shows that the p-values of joy–sadness, trust–disgust, fear–anger, surprise–anticipation, and negative–positive relations are close to zero. Finally, neural network architectures, including 1DCNN, LSTM, Multiple-Layer Perceptron, and BERT, were trained and tested in a COVID-19 multi-classification of sentiments and emotions (positive, negative, joy, sadness, trust, disgust, fear, anger, surprise, and anticipation). Our experiment attained an accuracy of 88.6% for 1DCNN at 1744 s, 89.93% accuracy for LSTM at 27,597 s, while MLP achieved an accuracy of 84.78% at 203 s. The study results show that the BERT model performed the best, with an accuracy of 96.71% at 8429 s.

The increased number of social media platforms allows different groups of people around the globe to express their thoughts and sentiments on such media. Such ideas and opinions might implicate the user's social and political perspectives. Those perspectives are subject-specific inputs that have been useful to data science researchers to do community detection and sentiment analysis studies. Research studies utilize the rich information from social media, such as Twitter, to gain a better knowledge of public opinion in societies. In our study, we proposed a machine learning-based algorithm to predict and classify the textual data from Twitter about the 2020 US election campaign. The opinion poll of the presidential elections might be inaccurate or bias, resulting in providing significant negative effects with voters. The dataset was collected during the 2020 presidential election campaign toward the voting day. In addition to the original tweets, we generated fake tweets added to the dataset. Before organizing the comprehensive data and validation, we have done data cleaning and screening to get a reasonable and sensible correlation. For comparison, we used a total of five classification algorithms, such as Linear Support Vector Classification (LSVC), Random Forest (RF), Decision Tree (DT), Logistic Regression, and Naive Bayes. The study found that Trump was more popular than Biden on Twitter. Even though he was more famous than his rival, the study suggested that Joe Biden has a higher average percentage of positive sentiments than Donald Trump nationally. On the other hand, Donald Trump has a higher average percentage of negative sentiments than Joe Biden. In favor of Joe Biden compared to Donald Trump during the 2020 US presidential election, which led to the prediction that Joe Biden would outperform Donald Trump in the 2020 election. Furthermore, adding fake tweets into the dataset has slightly decreased Naive Bayes, Decision Tree, and LinearSVC model performances, but it slightly improved the Logistics Regression model classifier. Retrospectively, the Twitter data could have successfully predicted the US presidential election outcome by factoring in the proportion of positive and negative sentiment for the leading candidates. The study concludes that social media data-based sentiment analysis provides an accurate prediction model for American presidential elections.

The increased social media usage in modern history instigates data collection from various users with different backgrounds. Mass media has been a rich source of information and might be utilized for countless purposes, from business and personal to political determination. Because more people tend to express their opinions through social media platforms, researchers are excited to collect data and use it as a free survey tool on what the public ponders about a particular issue. Because of the detrimental effect of news on social networks, many irresponsible users generate and promote fake news to influence public belief on a specific issue. The U.S. presidential election has been a significant and popular event, so both parties invest and extend their efforts to pursue and win the general election. Undoubtedly, spreading and promoting fake news through social media is one of the ways negligent individuals or groups sway societies toward their goals. This project examined the impact of removing fake tweets to predict the electoral outcomes during the 2020 general election. Eliminating mock tweets has improved the correctness of model prediction from 74.51 percent to 86.27 percent with the electoral outcomes of the election. Finally, we compared classification model performances with the highest model accuracy of 99.74634 percent, precision of 99.99881 percent, recall of 99.49430 percent, and an F1 score of 99.74592 percent. The study concludes that removing fake tweets improves the correctness of the model with the electoral outcomes of the U.S. election.

Numerous valuable information is available on the Internet, and many individuals rely on mass media as their primary source of information. Various views, comments, expressions, and opinions on social networks have been a tremendous source of information. Harvesting free, resourceful information through social media makes text mining a powerful tool for analyzing public opinions on various issues across diverse social networks. Various research projects have implemented text sentiment analysis through machine and deep learning approaches. Social media text often expresses sentiment through complex syntax and negation (e.g., implicit and double negation and nested clauses), which many classifiers mishandle. We propose hybrid negation, a clause-aware approach that combines (i) explicit/implicit/double-negation rules, (ii) dependency-based scope detection, (iii) a TextBlob back-off for phrase polarity, and (iv) an MLP-learned clause-weighting module that aggregates clause-level scores. Across 156,539 tweets (three-class sentiment), we evaluate six negation strategies and 228 model configurations with and without SMOTE (applied strictly within training folds). Hybrid Negation achieves 98.582% accuracy, 98.196% precision, 98.189% recall, and 98.193% F1 with BERT, outperforming rule-only and antonym/synonym baselines. Ablations show each component contributes to the model’s performance, with dependency scope and double negations offering the largest gains. Per-class results, confidence intervals, and paired tests with multiple-comparison control confirm statistically significant improvements. We release code and preprocessing scripts to support reproducibility.