USE OF NLP TECHNIQUES AND CONVOLUTION NEURAL NETWORK FOR DETECTING SENTIMENT OF MOVIE REVIEWS

In recent years, there has been a significant increase in the amount of data generated on the internet, particularly in the form of text or reviews. Understanding the thoughts, emotions, and attitudes concealed in tweets, emails, comments, and reviews is difficult, but crucial for market analysis, brand monitoring, social media tracking, and customer support. Sentiment analysis of reviews is a challenging task, as it requires the ability to understand the nuances of human language and the ability to distinguish between positive and negative opinions. Natural Language Processing (NLP) techniques have been widely used for sentiment analysis, but they often fall short in detecting sarcasm, irony, and context-dependent sentiment. To overcome these limitations, Convolution Neural Networks (CNNs) have been employed in sentiment analysis tasks. This paper presents an approach that combines NLP techniques and CNNs for detecting the sentiment of movie reviews. The proposed approach uses a preprocessing step to remove noise and irrelevant information, followed by feature extraction using NLP techniques. The extracted features are then fed to a CNN model for sentiment classification. Experimental results show that the proposed approach outperforms existing approaches in terms of accuracy and robustness, making it a promising tool for sentiment analysis of movie reviews. This can be useful for understanding audience reactions to movies, identifying areas for improvement in movie production, and even predicting box office success.