As technology advances and online shopping becomes more prevalent, customer reviews have become a crucial tool for assessing the quality and value of products. Customer reviews can offer valuable information about their experiences of other buyers with a particular product, including their thoughts, sentiments, and experiences. By analyzing and extracting useful information from customer reviews, future buyers can make more informed decisions about the products they are considering. Using techniques from natural language processing (NLP) and machine learning, sentiment analysis classifies the tone of a customer review as either positive or negative. The task of parsing through text data involves identifying the overarching sentiment, emotional tenor, and opinion expressed in a review. In this paper, we study sentiment analysis of client reviews using machine learning algorithms with different vectorization techniques. The proposed approach is structured into three stages. The first stage applies pre-processing which is to extract the valuable words and reduce noisy data. And in the next stage, feature extraction was performed by different vectorization techniques such as Bag-Of-Word (BoW), TF-IDF (Term Frequency Inverse Document Frequency), N-grams. After extracting the features from text data, the final stage is classification and predictions based on machine learning approaches. We evaluated the proposed model on three different reviews datasets which are Fine Food, Yelp and Spotify reviews. The experimental results are evaluated using metrics such as accuracy, f1-score, recall and precision and K-fold cross-validation, confusion matrix and runtime