Customer Sentiment Analysis for Service Issue Detection Using Negative Sentiment

Prajapati, Anil Lalbahadur (2024) Customer Sentiment Analysis for Service Issue Detection Using Negative Sentiment. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (952kB) | Preview
Preview	PDF (Configuration Manual) Download (953kB) | Preview

Abstract

Nowadays, accessing and consuming digital media is lot easier and cheaper than ever before. With this growing demand it is becoming crucial for the product developer to be more accurate while delivering their products. However, it is challenging to deliver a seamless experience and often end up releasing product with issue. Detecting and addressing this becomes crucial for the developers. Develops mostly rely testers and developer forums to address this issue which can be slow and is not able to address all the issue. This work aims to help the product developers to understand and react to the launch issues by understanding the negative sentiment among the user and using that to detect possible issues and address the issue quickly. This study demonstrate the use of Machine Learning (ML) and LLM to detect the negative sentiment and issue with product and services. The user of BERT for the sentiment analysis proved to be contextually accurate compared to VADER and LLM model such as Llama is able to identify issue in those negative sentiment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jilani, Musfira UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HF Commerce > Customer Service
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 10:22
Last Modified:	04 Sep 2025 10:22
URI:	https://norma.ncirl.ie/id/eprint/8775

Actions (login required)

View Item