Sentiment analysis of customer reviews on food ordering portals of Bangladesh using natural language processing

Abstract

In recent years, the popularity of online food ordering services has surged, offering consumers a convenient way to order food from restaurants and have it delivered to their doorstep. During this period, HungryNaki and Foodpanda Bangladesh have been identified as key contributors to the growth and advancement of the online food delivery market. This study aims to anticipate the sentiments of Bangladeshi customers towards online meal ordering services, with a specific focus on Foodpanda Bangladesh and HungryNaki. We created a new dataset for this research, subjected it to preprocessing and employed six machine learning models and three deep neural network models. In the machine learning approach, the Random Forest Classifier demonstrated excellence in accuracy, precision, and recall, achieving an accuracy rate of 80.31%. On the other hand, the BERT Classifier performed effectively in the deep learning approach, reaching a peak accuracy of 89%. Despite challenges such as data ambiguity and imbalances in the dataset, our findings underscore the potential of the BERT model in sentiment analysis, offering valuable insights for future research in this field.