Online reviews play a critical role in the success of any business. It is an important tool that affects the decisions of both customers and vendors. Reviews also tell an organization's decision-makers when and how to make changes to their quality plan. Product makers depend on reviews to uncover their products' faults and get competitive intelligence about their competitors. So, it is important to be sure that reviews are real and represent a real customer opinion. Fabricated reviews have the potential to mislead the general audience, leaving people unsure of the review. In literature, different approaches have been proposed to address the problem of deceptive reviews. In this work, we aim to explore the area's current state, its implications, limitations, and possible future paths. We focused on the recent technologies and theories that were implemented to detect deceptive reviews. This review can be useful for anyone interested in detecting deceptive online reviews. This paper is part of another research focusing on the reliability of deceptive online reviews, to develop a comprehensive evaluation framework to validate online reviews.
Key words: Online Reviews; Deception; Fake Opinion; Machine Learning; Detection
|
