Sentiment Analysis of Product Reviews using Rule-based and Deep-Learning Models

Abstract

This study analyses the feelings and opinions expressed in product reviews by utilizing NLTK (Natural Language Toolkit) and deep learning models to forecast customer sentiments and evaluate the probability of product purchases based on the review information available. The study examines the sentiment analysis applied to the Flipkart product reviews using a sentiment dataset. The NLTK, VADER, and RoBERTa models are evaluated for their effectiveness in predicting the sentiment of the customers. The analysis shows that the VADER, as a rule-based model is efficient in handling short and simple reviews but faces challenges with more complex sentiments. Meanwhile, RoBERTa outperforms VADER, with a Mean Absolute Error (MAE) of 0.12 and an R2 value of 0.85. The comparative study shows the ability of RoBERTa to capture subtle emotions in customer reviews and accurately understand customer feedback, proving to be valuable in e-commerce for optimizing product recommendations and customer satisfaction.