The enormous quantity of information originated and distributed on societal communications each and every day highlights the need for knowledge-extraction processes to be automated. Sentiment investigation is an energetic area of information extraction investigate that faces numerous problems. Any company should be eager to hear from its customers. Customers primarily rely on reviews to decide where to eat. Sentiment analysis is critical in categorizing restaurant reviews as positive, negative, or disinterested in organize to assess whether the cuisine is good, secure, and worth choosing over other restaurants. In this study, the Yelp dataset for restaurant reviews is used to examine various word embedding algorithms, similar as Bag of Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), GloVe,Word2Vec, and Doc2Vec. Supervised Machine Learning (ML) approaches such as Logistic Regression and Support Vector Machine are assessed using performance metrics similar as F1-Score, Accuracy, Recall, and Precision. Comparable results show that combining a Support Vector Machine and TF-IDF word embedding technique yielded results with a 98% accuracy. We investigate several pre-processing strategies and apply various features and classifiers.