Fake Review Detection on Amazon Dataset Using Classification Techniques

Machine Learning

The Amazon dataset, with its extensive and diverse collection of reviews, offers a rich resource for studying fake review detection. The ubiquity of online reviews has transformed the decision-making process for consumers, with platforms like Amazon hosting millions of product reviews. However, the prevalence of fake reviews poses significant challenges to maintaining the integrity and reliability of this user-generated content. This survey paper provides a comprehensive review of the state-of-the-art techniques for detecting and classifying fake reviews on the Amazon dataset. We examine various approaches, including text-based analysis, sentiment analysis, and behavioral analysis, along with machine learning and deep learning methods. By analyzing the strengths and limitations of these techniques, we aim to provide a clear understanding of the current landscape and identify future directions for research in this critical area. This survey highlights the importance of developing robust detection mechanisms to ensure the trustworthiness of online reviews and supports the ongoing efforts to combat fraudulent activities in e-commerce. Keywords— Fake Review, Classification, Amazon, Dataset.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.