Social media platforms like Twitter provide major means for individuals to express their opinions on various topics; therefore, a need for complex tools to distinguish between negative and positive attitudes in textual content. With consideration for the most suitable models for precisely classifying sentiments within social media data, this study aims to evaluate the efficacy of machine learning algorithms in analyzing sentiment text that people post or comment on Twitter, thus bridging the research gap in the analysis of sentiment in an understudied domain. a set of machine learning algorithms was applied along with feature extraction methods, including TF-IDF and Natural Language Processing (NLP). With an accuracy of 93%, the Random Forest (RF) model proved to be the most effective among other models, Because of its exceptional capacity and generating accurate and dependable results on textual data, the Random Forest (RF) model proves in the study to be the most optimal choice for sentiment analysis textual.
Al-Agele et al. (Mon,) studied this question.