Today people, exchanging their thoughts through online web forums, blogs, and different platforms for social media. In online shopping, they are giving reviews and opinions on other various products, brands, and services. Their thoughts towards a product are do not only purchase decisions of the consumers but also improves the product quality about their requirements and find out the product's particular problem and get an excellent solution on that product. The present system concentrate on the peer-reviewed review model (User-generated review) and global qualification i.e., rating and, tries to classify the semantic aspect and emotions at the time aspect level from the data to investigate general sense feel of the reviews. SJASM represents each review document in the format of opinion pairs and, along with simulating the terms of appearance and the corresponding opinion words of the study, consideration for the hidden aspect and the sentiment detection. The current system is designed as a recommendation system Physiological Language Processing (NLP) Technique to read reviews and using Naïve Baye's Classification automatically. We have also extracted the thoughts of the product characteristics. Here admin can analyze the opinion pair that actually what is defect in the finished product so in future the market of that product will increase. This system to extract product aspects and corresponding opinions from consumer ratings on the internet. Different machine learning algorithms are discussed in Naïve Bayes is considered in order to classify of sentiments, and variables such as precision, recall, F-score, and accuracy are used to assess a classifier's performance.