Published Paper Details:

Sentiment analysis in social media has garnered significant attention due to its applications in understanding public opinion, market trends, and user feedback. This research paper explores the effectiveness of sentiment analysis techniques leveraging artificial intelligence (AI) in various social media platforms. It examines the methodologies, challenges, and advancements in AI that contribute to enhancing sentiment analysis accuracy and applicability. The study evaluates several AI models, including Support Vector Machines (SVM), Naive Bayes, Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), Convolutional Neural Networks (CNN), and transformer-based architectures such as BERT. By comparing these models across multiple metrics--accuracy, precision, recall, F1-score, and ROC-AUC--our findings highlight the superior performance of modern deep learning approaches, particularly BERT. Additionally, the paper discusses practical applications and case studies, illustrating the real-world impact of AI-powered sentiment analysis in areas such as crisis management, political analysis, brand reputation management, and customer service improvements.