Paper Contents
Abstract
Online reviews are crucial for consumer decision-making, yet the prevalence of fake reviews undermines their reliability. This study explores the application of machine learning techniques to detect fake reviews, focusing on Natural Language Processing (NLP) and deep learning models like Long Short-Term Memory (LSTM) networks. The study evaluates these methods based on accuracy, efficiency, and scalability, and compares the trade-offs between simpler and more complex models. Challenges such as obtaining quality training data and adapting to evolving fake review tactics are also examined. To address these issues, the study proposes and tests hybrid detection systems that integrate multiple techniques. The goal is to enhance the integrity and trustworthiness of online review platforms, making them more reliable resources for consumers.
Copyright
Copyright © 2024 Damarasingi Sai Teja. This is an open access article distributed under the Creative Commons Attribution License.
