Abstract:
In Today's internet world, online activities are growing exponentially and generating a tremendous number of online reviews and ratings, which are a valuable source of information for customers primarily associated with the purchase of marketing, selecting a restaurant, finding products, health, and services, etc. Therefore, online reviews are a crucial part of people's everyday decisions on what to buy, where to buy, where to eat, where to stay, which doctors to see, and what to select based on positive, negative, and neutral. Fake reviews not only mislead innocent clients and influence customers' choice, leading to inaccurate descriptions and sales. However, there is still a significant requirement for a survey that can examine and summarize the various methodologies that are now available. This paper summarizes the existing datasets and the techniques they have acquired to represent the task of fake review detection. In addition, it examines the various feature extraction strategies that are currently available. Finally, we discuss the present gaps in this research area and potential coming directions in this field. We analyze and compare two various features extraction strategies and six various machine classification techniques.
Page(s):
141-158
DOI:
DOI not available
Published:
Journal: Journal of Theoretical and Applied Information Technology, Volume: 100, Issue: 13, Year: 2022
Keywords:
machine learning
,
deep learning
,
feature engineering
,
Fake review detection