SENTIMENT ANALYSIS FOR PRODUCT RATING SYSTEM
Abstract
This project presents the development and evaluation of a Sentiment Analysis for Product Rating System designed to augment traditional numerical rating systems by providing contextual insights from textual reviews. Current product rating mechanisms often lack the granularity to explain why a particular rating was given, leading to ambiguous interpretations and limiting actionable feedback for businesses. To address this, The system leverages advanced Natural Language Processing (NLP) techniques to automatically classify the sentiment of product reviews.The methodology involved designing a modular architecture encompassing a data ingestion layer, a text preprocessing module, and a core sentiment classification engine utilizing a fine-tuned BERT model. Rigorous system testing, conducted on a diverse dataset of 50,000 product reviews, demonstrated the system's effectiveness.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.