AI Powered Detection of Deceptive Product Feedback A Review of Methods, Models, and Future Directions

Online reviews have become a crucial part of consumer decision making, significantly influencing product reputation and sales. However, the rise of fake or manipulated product feedback poses a serious threat to trust, transparency, and the credibility of e commerce platforms. This paper presents a comprehensive review of how Artificial Intelligence AI and Machine Learning ML techniques are used to detect and prevent fake reviews. It highlights the evolution of AI based models, including Natural Language Processing NLP for text analysis, deep learning for feature extraction, and sentiment analysis for identifying deceptive patterns. The study also explores recent advancements such as transformer based models BERT, RoBERTa , multimodal analysis combining text, image, and user behavior, and graph based learning to enhance detection accuracy. Additionally, the paper discusses benchmark datasets, evaluation metrics, challenges in cross domain generalization, and the ethical implications of automated moderation. This review provides insights into current trends, identifies open research challenges, and outlines future directions for developing robust, transparent, and trustworthy AI systems to combat fake product feedback. Manish Adawadkar "AI-Powered Detection of Deceptive Product Feedback: A Review of Methods, Models, and Future Directions" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-9 | Issue-5 , October 2025, URL: https://www.ijtsrd.com/papers/ijtsrd97583.pdf Paper URL: https://www.ijtsrd.com/computer-science/artificial-intelligence/97583/aipowered-detection-of-deceptive-product-feedback-a-review-of-methods-models-and-future-directions/manish-adawadkar