With the developing technology, social media, forum sites and blocks have been widely used. People are now using these channels very widely and they share their feelings and thoughts in these environments. Therefore, natural language processing applications have started to become a more popular topic with each passing day. One of the most popular topics in natural language processing is sentiment analysis. In sentiment analysis, subjective information is extracted by making examinations according to certain criteria. In this study, the IMDB data set was used to perform sentiment analysis. The IMDB dataset is one of the largest datasets on this subject, consisting of movie reviews. This dataset contains users' comments about movies. In the study, firstly, the data preprocessing step was carried out. Then, the prepared data set was classified in classical machine learning classifiers and the proposed ESA-based model. The proposed ESA-based model was more successful than the classical machine learning classifiers in analyzing the texts in the IMDB dataset, and the proposed deep model achieved an accuracy of 85.57%.