Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199214,
        author = {Manav Anodhe},
        title = {Fake Review Detection in E-commerce},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15414-15418},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199214},
        abstract = {The rapid expansion of e-commerce platforms has significantly transformed consumer purchasing behavior, making online reviews one of the most influential factors in decision-making. Customers increasingly depend on reviews to evaluate product quality, reliability, and overall satisfaction before making a purchase. However, this growing dependence has also led to the widespread problem of fake or deceptive reviews, which are intentionally created to manipulate product ratings and mislead potential buyers. Such reviews can artificially promote low-quality products or unfairly damage the reputation of competitors, thereby disrupting the fairness and transparency of digital marketplaces.
Recent studies indicate that nearly 20% to 30% of online reviews may be fraudulent, posing a serious challenge to both consumers and e-commerce platforms. Traditional detection methods, such as manual moderation and rule-based filtering, are no longer sufficient due to the massive volume of data and the evolving nature of spam techniques. In this context, Machine Learning (ML) has emerged as a powerful and scalable solution for identifying fake reviews with high accuracy and efficiency.
Machine learning models analyze multiple aspects of review data, including textual content, linguistic patterns, reviewer behavior, and metadata attributes such as timestamps and rating distributions. Advanced techniques such as Natural Language Processing (NLP) and deep learning models enable systems to capture contextual meaning and detect subtle irregularities that are often missed by conventional approaches. Furthermore, hybrid models that combine behavioral and textual features have shown improved performance in real-world scenarios.
This research paper presents a comprehensive study of fake review detection in e-commerce using machine learning techniques. It explores various methodologies, evaluates model performance on a large dataset, and discusses key challenges such as data imbalance, lack of labeled data, and continuously evolving spam strategies. The paper also highlights future directions, including the integration of explainable AI and secure technologies, to build more reliable and trustworthy review systems.},
        keywords = {},
        month = {April},
        }