A Brief Study on the Fake Review Detection methods on Ecommerce Websites using Machine Learning, Artificial Intelligence, and Data Science

Abstract

Abstract: Customer reviews play an important role in influencing purchasing decisions on ecommerce websites, which are becoming increasingly popular for online shopping. The appearance of phoney reviews, on the other hand, might have a substantial impact on the credibility and dependability of these platforms. As a result, fake review identification has developed as a significant study field, with machine learning, artificial intelligence, and data science techniques emerging as promising approaches to solving this issue. In this review paper, we present a complete overview of the most recent strategies for detecting fraudulent reviews on ecommerce websites, with a focus on the use of machine learning, artificial intelligence, and data science. We evaluate the usefulness of several approaches, such as feature-based, behaviour-based, and deep learning-based techniques, in detecting false reviews. We also discuss the obstacles and future directions in fake review detection research, including imbalanced datasets, adversarial attacks, multimodal fake reviews, real-time detection, explainability, ethical implications, and domain knowledge incorporation. The goal of this review article is to provide a thorough overview of the present research environment in false review identification on ecommerce websites utilising machine learning, artificial intelligence, and data science, as well as to guide future research in this area