SIIRMLApr 21, 2020

Quarantine Deceiving Yelp's Users by Detecting Unreliable Rating Reviews

arXiv:2004.09721v1
Originality Synthesis-oriented
AI Analysis

This addresses the issue of review fraud for consumers and businesses on platforms like Yelp, but it appears incremental as it combines existing detection methods.

The paper tackles the problem of unreliable reviews on Yelp by detecting deceiving users using review spike detection and spam detection techniques, finding that over 80% of accounts are unreliable and over 80% of highly-rated businesses are spammed.

Online reviews have become a valuable and significant resource, for not only consumers but companies, in decision making. In the absence of a trusted system, highly popular and trustworthy internet users will be assumed as members of the trusted circle. In this paper, we describe our focus on quarantining deceiving Yelp's users that employ both review spike detection (RSD) algorithm and spam detection technique in bridging review networks (BRN), on extracted key features. We found that more than 80% of Yelp's accounts are unreliable, and more than 80% of highly-rated businesses are subject to spamming.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes