ReviewGuard: Real-Time Detection of Fake Online Reviews

DOI

10.2991/978-94-6239-713-2_40How to use a DOI?

Keywords

Fake Review Detection; DeBERTa v3; Browser Extension; XAI; E-commerce Reviews

Abstract

Online reviews strongly influence purchasing choices in today’s e-commerce platforms. However, due to an increase in promotional, spammy, and deceptive reviews, it has often become difficult for a consumer to get a correct idea about the quality of a product. To mitigate this issue, this paper proposes a solution in the form of a browser extension called ReviewGuard, which can identify fake reviews during real-time web surfing. The system extracts live review text from the Document Object Model (DOM) and conducts real-time analysis using a fine-tuned DeBERTa v3-small transformer model, which was initially pretrained on English texts. The model focuses on identifying manipulative language, vague promotional content, and spam-like text patterns, instead of simply flagging AI-generated text. To enhance reliability, the system combines the confidence scores from the neural model with contextual platform indicators, such as the Verified Purchase badge on e-commerce sites like Amazon. The framework was tested using the Amazon Fake Reviews dataset, which includes 40,432 reviews, with an 80–20 split for training and testing. Experimental results show strong performance, with approximately 97% overall accuracy and an F1-score of 0.9696 on the test dataset, demonstrating balanced detection capability (0.9701 F1 for deceptive reviews and 0.9691 for genuine reviews). In addition, the system includes an explainable AI component (XAI) that generates short explanations within the browser interface, showing why the review is flagged.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - K. Giriprasath
AU  - Atharv Bandekar
AU  - Tejas Kavanthankar
AU  - Shubham Govekar
AU  - Akshay Shetye
PY  - 2026
DA  - 2026/06/25
TI  - ReviewGuard: Real-Time Detection of Fake Online Reviews
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 537
EP  - 548
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_40
DO  - 10.2991/978-94-6239-713-2_40
ID  - Giriprasath2026
ER  -