Fake Review Detection in Online Platforms: A Machine Learning and Deep Learning Approach

With the rapid growth of e-commerce platforms, online reviews have become a critical factor influencing consumer decision-making. However, the increasing presence of deceptive or fake reviews poses a serious threat to trust and transparency in digital marketplaces. Traditional machine learning techniques often fail to capture the contextual semantics of textual data, limiting their effectiveness in identifying sophisticated fake reviews. This research proposes a hybrid fake review detection system that integrates Natural Language Processing (NLP), traditional machine learning models, and a lightweight transformer-based model, DistilBERT. The system performs automated data collection, preprocessing, contextual embedding, and classification to distinguish between genuine and fake reviews. Additionally, real-time analysis is achieved through a Flask-based deployment architecture. Experimental insights suggest that transformer-based models significantly improve detection accuracy while maintaining computational efficiency. The proposed system provides a scalable and practical solution for enhancing the credibility of online review systems.