Advanced Sentiment Analysis and Topic Modeling on E-Commerce Reviews: A Comparison Study Using BERT and RoBERTa on Flipkart and Amazon

Chauhan, Himani (2023) Advanced Sentiment Analysis and Topic Modeling on E-Commerce Reviews: A Comparison Study Using BERT and RoBERTa on Flipkart and Amazon. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (590kB) | Preview

Abstract

Our project delves into the realm of advanced sentiment analysis and topic modeling, focusing on e-commerce reviews from Flipkart and Amazon, two major platforms. Using state-of-the-art natural language processing models, namely Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT (RoBERTa), we aim to gain a deeper understanding of customer sentiments. By utilizing pre-trained transformer models and fine-tuned sentiment analysis techniques, we were able to improve the accuracy of classifying customer sentiments. Furthermore, we conducted a comparison between Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT (RoBERTa) to evaluate which model better captures the nuances of e-commerce sentiments. We took our analysis a step further by implementing Latent Dirichlet Allocation (LDA) on the embeddings generated by Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT (RoBERTa). By doing so, we aimed to uncover underlying themes within the reviews, providing valuable insights into the factors that drive customer opinions. This comparative study enables us to gain a comprehensive understanding of the effectiveness of each model in capturing the diverse aspects of e-commerce sentiments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 May 2025 13:19
Last Modified:	07 May 2025 13:19
URI:	https://norma.ncirl.ie/id/eprint/7504

Actions (login required)

View Item