E-commerce is becoming more and more popular in this digital era since it allows customers to order things online and have them delivered right to their doorsteps. Reviews now have more significance as consumers use them to make informed decisions about what to buy. By classifying and learning from reviews, machine learning might help with the laborious work of sifting through hundreds of them. Sentiment analysis is a fundamental function of natural language processing (NLP) that focuses on comprehending attitudes and emotions. This research employs supervised learning techniques to analyze the feelings of product evaluations on Amazon. Thousands of reviews in various categories may be found in the dataset that was used. Recurrent neural networks (RNNs), among other NLP models, are tested for the purpose of classifying reviews into positive, negative, and neutral sentiments. The models are evaluated by applying recall, accuracy, and precision. Investigations are being conducted on the implications of sentiment analysis findings for companies and consumers using the Amazon platform. This study provides information on sentiment analysis on the dataset from Amazon and its useful applications. E-commerce is growing in popularity, and machine learning-based sentiment analysis might help evaluate massive volumes of data and effectively identify emotions. For the purpose of classifying emotions, a variety of machine learning techniques have been used, such as K-means clustering, decision trees (DTs), convolutional neural networks (CNNs), support vector machines (SVMs), and Bayesian networks (BNs). This study compares previous research and offers a real-time sentiment analysis system to monitor common feelings and provide recommendations that users would find acceptable. A key component of natural language processing (NLP) is sentiment analysis, which classifies sentiment polarity. This study offers a generic method for classifying sentiment in online product reviews from Amazon.com and aims to address problems in sentiment analysis. Investigations into categorization at the sentence and review levels are conducted, with encouraging outcomes. There is also mention of future work on sentiment analysis.