Brand Reviews of e-wallet applications using Twitter sentiments

Ransing, Snehal Nagnath (2023) Brand Reviews of e-wallet applications using Twitter sentiments. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (20MB) | Preview
Preview	PDF (Configuration manual) Download (911kB) | Preview

Abstract

Sentiment Analysis or opinion mining of the customer has become essential for a business to gain an upper hand in comparison to their competitors. To increase the footfalls of any product, it is important for a business to be aware of their current loopholes and the area they are lacking to provide services to the customer. Twitter being the most successful and popular platform of expression, users around the world grab the opportunity to comment and express their views. This study deals with capturing such tweets and analysing their expressions by judging the user sentiments regarding the product. Live twitter data is extracted for e-wallet apps used in India by making use of module with 35000 records, 7000 each for brand namely GooglePay, AmazonPay, Phonepe, Paytm, PayPal. Model development is done and evaluated using ML Models like Liner SVC (89% accurate), KNN-algorithm (56% accurate). Apart from ML, Deep Learning model namely BERT is used which provides an accuracy of 90% and Roberta provides 89% accuracy. With the model training and evaluation, Brand analysis is performed for negative areas where the outcomes are a brand must focus on marketing in certain regions, improve their interfaces and set up a proactive support team. Manual analysis also performed on the test data and predicted data to understand difference between accuracy.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nayak, Prashanth 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 > Electronic Commerce Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	25 May 2023 14:10
Last Modified:	25 May 2023 14:10
URI:	https://norma.ncirl.ie/id/eprint/6642

Actions (login required)

View Item