The study explores Twitter Sentiment Analysis (TSA) using Natural Language Processing (NLP) to understand societal views, trends, and feelings. The research involves data collection, pre-processing, feature extraction, sentiment analysis, model construction, and visualization. The data is then processed to address issues like extraneous characters, capitalization, and data errors. Sentiment analysis categorizes tweets into positive and negative. The NLP algorithm is central to sentiment classification, and the paper builds, trains, and assesses various machine learning models. Word clouds depict sentiment distribution, identify frequently occurring phrases, and emphasize sentiment trends over time. Potential roadblocks include data quality issues, careful algorithm selection, and model dependability. The sentiment analysis model demonstrated good accuracy and a balanced F1-score, demonstrating its competency in sentiment categorization. The study contributes to the emerging discipline of sentiment analysis by demonstrating how valuable insights can be extracted from massive amounts of social media data.