Leveraging LSTM and Multinomial Naive Bayes for Nuanced Textual-Based Sentiment Analysis

People all across the world express and share their points of view publicly on many platforms about different topics. Analyzing the common man’s opinions and perspective towards any movies, services, products, social events, politics, and company strategies in the form of Texts, Reviews (from sources such as BookMyShow and MakeMyTrip) and social network posts (mostly from X and Facebook) provides with some sort of textual documents, that serve as source for sentiment analysis. So, to enhance the efficacy of the sentiment reviews, we have proposed a model that incorporates Artificial Neural Networks (ANN) such as Long Short Term Memory (LSTM) and Natural Language Processing (NLP) namely Multinomial Naive Bayes (MNB) evaluated on the datasets of IMDB, X (Twitter) Review and Amazon Product Review. From the experimentation, the obtained outcome signifies that the proposed approach LSTM and MNB reveals supremacy with the compared state-of-the-art approaches. It can be inferred that the demonstrated model is a fruitful and reliable approach that is effective in analyzing the sentiments. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.