Identify Counterfeit Product Reviews or AI Text by Bots on E-commerce Websites

Massey, Avis (2023) Identify Counterfeit Product Reviews or AI Text by Bots on E-commerce Websites. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (993kB) | Preview

Abstract

Digital technologies are becoming a part of our day-to-day decision-making. Potential buyers explore reviews and experiences from the current users of the products and services on various online platforms that influence their buying decisions. Being said that, the use of these tools has been widely used to manipulate the perceptions of consumers and influence the buying decision in favour of the entities, making fake reviews a critical challenge. Potential buyers are influenced by the popular service providing websites and e-commerce platforms through encouraged user feedback. With the rising dependency on product feedback, it becomes paramount for the customers to be able to identify the genuine feedback from the pool of false reviews. To vanquish this challenge for potential buyers, we move to advanced machine learning and deep learning techniques, applying models like LSTM, CNN, and SVM for deep learning and BERT, Roberta, Albert, and DistilBERT for transformer models. The crucial component of consumer decision-making has shifted to online reviews, which people share based on their actual experiences. In all appearances, the increase in exploitation of technology is leading to misguided consumer choices by generating spam and fake reviews to either boost or undermine a business. Marketers can utilise this analysis to ensure a transparent and trustworthy online marketplace by using tailored strategies and to customer preferences. We evaluate models’ performance based on accuracy and weighted F1-score, which demonstrates the superior capabilities of a model in detecting false reviews.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Anant, Aaloka UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HF Commerce > Marketing > Consumer Behaviour 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:	Ciara O'Brien
Date Deposited:	18 May 2025 13:29
Last Modified:	18 May 2025 13:29
URI:	https://norma.ncirl.ie/id/eprint/7569

Actions (login required)

View Item