Utilizing the Transformer models for Analysing Deceptive Reviews and Aspects of the reviews

Vinayagamurthy, Santhosh (2022) Utilizing the Transformer models for Analysing Deceptive Reviews and Aspects of the reviews. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (951kB) | Preview

Abstract

The customer posts their reviews of a product on social media platforms and on e-commerce platforms about a product. These reviews can be read by other customers who are also willing to buy the product. Getting an idea about a product before buying it is good for the customers. But some people or organizations in order to promote their products start posting fake positive reviews. Similarly, to demote their opponent’s business they post fake negative reviews. This can misguide the customer’s purchase decisions. Several researchers previously addressed this issue using machine learning and deep learning models. The transformer model like BERT, RoBERTa, and DeBERTa are used. A novel classifier DeBERTa has been explored in this research. The results show that the DeBERTa model outperforms the BERT and ROBERTA models and has achieved an F1 score of 93%

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 H Social Sciences > HF Commerce > Electronic Commerce Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	27 May 2023 11:39
Last Modified:	27 May 2023 11:39
URI:	https://norma.ncirl.ie/id/eprint/6680

Actions (login required)

View Item