Details - MACS Project System

Proposer: Timothy Yap
Title: Customer Feedback Analysis using Aspect-Based Sentiment Analysis
Goal: To train and provision an aspect-based sentiment analysis model that provides classifies the positive or negative customer feedback for a specific product or domain..
Description: Aspect-based sentiment analysis (ABSA) is a more detailed approach to sentiment analysis that goes beyond determining the overall sentiment of a piece of text. It focuses on identifying specific aspects or features of a product, service, or entity mentioned in the text and determining the sentiment expressed towards each of these aspects. This project aims to develop and evaluate a refined Aspect-Based Sentiment Analysis (ABSA) system to analyze customer feedback for a specific product or service domain. The goal is to provide detailed insights into customer opinions on various aspects of the product/service, enabling businesses to understand and address specific customer concerns more effectively.
Resources: BERT, Hugging Face
Background: Python, Pytorch, BERT, Scikit-learn
Url
Difficulty Level: Moderate
Ethical Approval: None
Number Of Students: 1
Supervisor: Timothy Yap
Keywords: machine learning, sentiment analysis, deep learning, transformer
Degrees: Bachelor of Science in Computing Science