Twitter Sentiment Analysis

Abstract

This study focuses on real-time Twitter sentiment analysis using Streamlit, TextBlob, and Tweepy, in order to gather and analyze data from Twitter and understand the sentiment of a particular topic, brand, or event. The study presents an efficient and scalable method of collecting tweets in real-time and analyzing their sentiment using TextBlob, a Python library for processing textual data. The results of the analysis are presented in an easy-to-understand format through a web-based dashboard built with Streamlit, allowing users to track the sentiment of a topic over time. The analyzed data, i.e. positive, neutral, or negative sentiment, is represented in graphical format on the dashboard, providing users with a visual representation of sentiment trends. The study also demonstrates the usefulness of such analysis for businesses, marketers, and researchers in understanding customer sentiment, identifying trends, and improving decision-making.