From Text To Insights: Building A Dynamic Dashboard For Sentiment Analysis - A Twitter Case Study

Abstract Platforms like Facebook, Instagram, Snapchat, and Twitter have offered individuals and groups a public forum to share their ideas on numerous social issues and themes in the age of social media. Twitter, a popular social media, and networking tool has evolved into an important source of real-time news and a hub for public opinion. Using Twitter data, this study investigates the possibility applying of sentiment analysis to automatically identify tweets as positive, negative, or neutral and then presenting the results visually, resulting in an in-depth analysis of public opinion. This research project compares two pre-trained sentiment analysis models, VADER and TweetNLP, to determine which model best suits this task. The project concludes with the creation of a dynamic dashboard for sentiment analysis based on Twitter data. This dashboard provides users with real-time insights from text data in a user-friendly way. The dashboard's architecture and style are proficient in analysing sentiment across a wide range of topics and effectively expressing findings using visual aids such as bar charts, time graphs, and word clouds. This research project improves on previous papers that have presented the benefits of sentiment analysis on historic static data by providing evidence for practical applications of real-time sentiment analysis techniques to organisations seeking to understand public sentiment, governments monitoring public opinion, and researchers studying sentiment across multiple topics, serving as a prototype for future development in these domains.