OPTIMAL LONG SHORT-TERM MEMORY (LSTM) HYPERPARAMETERS SELECTION USING PASTORALIST OPTIMIZATION ALGORITHM FOR CUSTOMERS SENTIMENT ANALYSIS

Abstract

ABSTRACT Users usually express their sentiments online which has great influence on the product customers buy. Sentiment analysis is the computational study of people’s emotions toward an entity. Sentiment analysis often faces the challenge of insufficient labeled data in Natural Language Processing (NLP) and other related areas. Long Short-Term Memory (LSTM) is one of the deep learning models widely used by researchers in solving sentiment analysis problem. However, they possess some drawbacks such as longer training time, more memory for training, easily overfits, and sensitivity to randomly generated parameters. Hence, there is a need to optimize the LSTM parameters for enhanced sentiment analysis. This research proposes an optimized LSTM approach using a newly developed novel Pastoralist Optimization Algorithm (POA) for enhanced sentiment analysis. The model was used to analyze sentiments of customers retrieved from Amazon product reviews. The performance of the developed POA-LSTM model shows optimal accuracy, precision, recall and F1 measure of 77.36%, 85.06%, 76.29%, and 80.44% respectively when compared with other optimization algorithm which is Biogeography-based optimization algorithm (BBO) with 76.10%, 78.64%, 83.50%, 80.99% and also the LSTM model with 71.62%, 78.26%, 74.23%, and 76.19% respectively. It was also observed that POA with 20 pastoralist population size performs better than other models with 10, 15, 25, and 30 populations.