Opinion extraction is another name for the classification used in sentiment analysis. Data mining is used to uncover favorable or negative product reviews by analyzing opinion data that is already available. Currently, a great deal of research is being done to automate sentiment analysis. In this work, we present a hybrid classification approach that combines three techniques: genetic algorithms (GA), support vector machines (SVM), and naïve bayes (NB). A method for restaurant reviews that is commonly used in the field of opinion grouping can be used to test the viability and benefits of the suggested methodologies. In order to increase the accuracy of the previously suggested method, we can also add another one, and finally conclusions are drawn in order to prove the effectiveness of this particular method in the field of sentiment analysis classification.