Fake Review Detection using Unsupervised Learning

People rely on online reviews to help them make the proper decisions in a world fueled by the internet. The impact of online reviews is important but also manipulates the people trust. The feedback from consumers helps to identify aspects that influence people decision towards the business. Having t...

Full description

Saved in:
Bibliographic Details
Published in2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) pp. 119 - 125
Main Authors Mothukuri, Radha, Aasritha, Aienavolu, Maremalla, Krishna Chaitanya, Pokala, Kesava Nandini, Perumalla, Gopi Krishna
Format Conference Proceeding
LanguageEnglish
Published IEEE 07.04.2022
Subjects
Business
Clustering
Clustering methods
Data communication
Data Science
Fake Reviews
Internet
Machine Learning
Unsupervised learning
Online AccessGet full text
DOI10.1109/ICSCDS53736.2022.9760908

Cover

More Information
Summary:People rely on online reviews to help them make the proper decisions in a world fueled by the internet. The impact of online reviews is important but also manipulates the people trust. The feedback from consumers helps to identify aspects that influence people decision towards the business. Having the right online reviews is important for a consumer to have trust towards the business. This venture proposes a clever methodology for this assignment, where it is inferred that key highlights characterize validity of an audit and join these elements into a grouping model. Our methodology is exceptionally generalizable and above all doesn't need express marking (Fake/Non Fake) of the review. Evaluation of our model on true client surveys for cafés taken from Yelp.
DOI:10.1109/ICSCDS53736.2022.9760908