NORMA eResearch @NCI Library

Identifying Fake Product Reviews

Yarlagadda, Mounika (2022) Identifying Fake Product Reviews. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (578kB) | Preview


Fake review detection can help us determine if a product review is real or false. Different methods can be used to achieve this, but we will focus on getting the result using machine learning methods. Our approach focuses on the content of the user review text. People who write fake reviews often choose topics or words to impress online customers, so their choice of words will be different from others. This word selection can be used to distinguish between false and false reviews. If these updates are received correctly, fake updates can be automatically removed once detected, which helps to provide only factual information and more specifically to companies and markets to customers.

The aim of the research is to develop an online technology system to detect and eliminate fake reviews with the aim of protecting the interests of customers, products, and e-commerce portals. The Flipkart Review dataset is analyzed with the help of Natural Language Processing, Supervised Learning Model and Deep Learning Model. Data was collected from a single shopping website (Flipkart) to identify counterfeit product reviews.

Item Type: Thesis (Masters)
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
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: 14 Mar 2023 15:42
Last Modified: 14 Mar 2023 15:42

Actions (login required)

View Item View Item