A major drawback with these approaches is that they follow a uniform weight assignment scheme for all the features. Researchers have focussed on extracting the features and giving them optimum weights (selected top k features) for final classification. The analysis uses the features of the product for determining the final polarity score. These opinions can be analysed using aspect-based sentiment analysis. In today’s digital age opinions enable effective decision-making ability of both the customer and manufacturer. This study covers an exhaustive study of sentiment analysis of movie reviews using CNN and LSTM by elaborating the approaches, datasets, results, and limitations. Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) is primarily implemented as powerful deep learning techniques in Natural Language Processing tasks. With ongoing advancement in deep learning, the capacity to analyze this content has enhanced significantly. Deep learning and machine learning have grown as powerful tools examining the polarity of the sentiments communicated in the review, known as ‘opinion mining’ or ‘sentiment classification.’ Sentiment analysis has become the most dynamic exploration in NLP (natural language processing) as text frequently conveys rich semantics helpful for analyzing. Although this information is unstructured, it is very crucial. These reviews and feedback draw incredible consideration from scientists and researchers to capture the vital information from the data. They are a significant source of entertainment and lead to web forums like IMDB and amazon reviews for users to give their feedback about the movies and web series. Movies are widely appreciated and criticized art forms. With the rapid growth of technology and easier access to the internet, several forums like Twitter, Facebook, Instagram, etc., have come up, providing people with a space to express their opinions and reviews about anything and everything happening in the world.