Sentiment Analysis of Twitter Posts on 5G Technology Using ML

In recent times, Twitter has emerged as a fascinating platform for conducting sentiment analysis and opinion mining due to its massive text corpus. Numerous users express their views on various trending topics and extensively use hashtags. This study aims to analyze and classify the sentiments of Twitter users regarding 5G technology using hashtags such as #5G and related ones. The study aims to understand users’ perceptions of 5G in terms of its mobility, reach, and impact on health. The emotions expressed about 5G are classified into positive, negative, and neutral categories using machine learning (ML) algorithms such as Support Vector Machine (SVM), Logistic Regression (LR), Multinomial Naive Bayes (MNB), and Random Forest, along with sentiment analysis libraries like Sci-kit and NLTK. The resulting classification model shows improved performance, evaluated using metrics such as accuracy, recall, and F1-score. Using SVM on a self-extracted dataset named “5G Myths,” an accuracy of 83.09% is achieved, while using LR, MNB, and Random Forest results in an accuracy of 80%, 75%, and 57%, respectively. The study demonstrates that it is feasible to identify the critical factors and information that shape public opinion about the acceptance or rejection of 5G technology on Twitter.