Twitter Scraping

Developed a comprehensive system for collecting and analyzing AI-related Twitter data using Tweepy and Twitter API v2. The project involved data collection based on targeted keywords, followed by efficient storage in MongoDB to ensure scalability and avoid duplication. Performed data preprocessing to clean and standardize tweet content, including removing noise such as URLs and mentions. Applied sentiment analysis using VADER to classify tweets into positive, negative, and neutral categories. Additionally, tweets were categorized into domains such as Natural Language Processing (NLP) and Computer Vision, with further analysis of sentiment trends and time-based patterns. Results were visualized using various techniques to provide clear insights into public sentiment and topic distribution. This project demonstrates strong capabilities in data engineering, natural language processing, and analytical visualization.