<![CDATA[In the digital age, social media has become a powerful platform for public expression and discourse, offering governments a real-time window into citizen sentiment. This research explores the application of Artificial Intelligence (AI), specifically Natural Language Processing (NLP) techniques, to analyze public sentiment on social media in response to government policies. Using data primarily sourced from Twitter, the study applies a BERT-based sentiment analysis model to classify public reactions into positive, negative, and neutral categories. The model achieved high performance with an accuracy of 89.2%, precision of 88.6%, and recall of 87.9%, outperforming traditional classifiers. Sentiment was analyzed across three key policy areas: fuel subsidy removal, education curriculum reform, and COVID-19 vaccination programs. Results indicate significant variations in public sentiment based on policy type, timing, and inferred demographic factors. A real-time sentiment analysis dashboard was developed to support policymakers in monitoring public opinion trends and improving communication strategies. This study demonstrates the potential of AI-driven sentiment analysis as a tool for enhancing data-informed governance, public engagement, and policy responsiveness.]]>
Copyrights © 2025
