War strategy assisted Bi-LSTM for sentiment analysis of customer review

Abstract

Sentiment analysis (SA) stands as a valuable tool for categorizing reviews to discern positive or negative sentiments. Satisfaction of customers holds a pivotal role in the realm of customer service. Presently, customer expression entails a significant volume of reviews on online platforms. For extracting useful information from massive reviews, the categorization of reviews into positive or negative SA is essential. For enhancing the efficiency of customer review detection, this work presents a war strategy algorithm (WSA)-bidirectional long short-term memory (Bi-LSTM) for customer review classification using the TripAdvisor dataset. Initially, the preprocessing stage is carried out, and the skip-gram-based word embedding is performed. For categorizing the extracted features, the deep learning model Bi-LSTM-WSA is presented. Accuracy and precision values achieved are 97.1% and 97.5% respectively.