The main goal of this project is to create a reliable system that extracts comments automatically from a variety of internet sources, including social media platforms, reviews, and articles. This project aims to develop a robust system for automated comment harvesting and sentiment analysis across diverse internet sources, including social media platforms, reviews, and articles. Leveraging the Octoparse tool, a web scraping bot is designed to efficiently extract comments, generating a substantial dataset for subsequent sentiment analysis and natural language processing (NLP). The system's core functionality revolves around NLP techniques, employing tools such as the Natural Language Toolkit (NLTK), Naïve Bayes, and VADER (Valence Aware Dictionary and Sentiment Reasoner) for sentiment analysis. The inclusion of VADER is particularly advantageous for its ability to discern the valence of words during sentiment analysis. The sentiment labels are predicted using a probabilistic machine learning technique, Naïve Bayes, based on preprocessed textual data. Key components of the sentiment analysis pipeline, including text processing and analysis, are facilitated by the comprehensive functionalities provided by NLTK, a versatile toolkit tailored for working with human language data. This integrated approach ensures scalability, accuracy, and efficiency in providing valuable insights to enterprises, researchers, and individuals seeking a comprehensive understanding of sentiments expressed in online comments.