IRO Journals
Recent Research Reviews Journal

Fake Review Detection Using Hybrid Transformer and Behavioral Analysis

Open Access
Published: 14 October, 2026
Pages: 440-452
  • Janagan A. , Janagan A.
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Assistant Professor, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Madhan P. , Madhan P.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Leo Aandrew G. , Leo Aandrew G.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
  • Mohammed Azardeen M. Mohammed Azardeen M.
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
    Student, Department of Computer Science and Engineering, NPR College of Engineering and Technology, Natham, Dindigul, India
view PDF
view PDF

How to Cite

A., Janagan, Madhan P., Leo Aandrew G., and Mohammed Azardeen M. 2026. “Fake Review Detection Using Hybrid Transformer and Behavioral Analysis”. Recent Research Reviews Journal 5 (2): 440-52. https://doi.org/10.36548/rrrj.2026.2.012.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Fake Review Detection
BERT Contextual Embeddings
Behavioral Feature Fusion
Linguistic Authenticity Signatures
SMOTE-Based Feature Balancing
Explainable Random Forest
SHAP–LIME Attribution

Abstract

Fake review detection is challenging when the deceptive information is semantically plausible while reviewer level and rating information are unusual. This paper presents Review Verity, a multi-modal fake review detection system that uses context, behavior and language representations in a single classification model. The language representation is created using static BERT-base-uncased model to generate 768-dimensional vector and account age, verified-purchase and multiple IP usage create three behavioral representation features. Review depth, subjectivity, Flesch readability, rating extremeness, sentiment agreement and rating disagreement create six linguistic representation features that combine with the vectors to produce 777-dimensional feature representation set. The feature set is normalized and rebalanced using SMOTE and then training is performed using 100 trees Random Forest classifier. SHAP and LIME models interpret the features and instances and the final model is deployed using FastAPI and React frameworks.

References

  1. Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. "Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding." In Proceedings of the conference of the North American chapter of the association for computational linguistics: Human Language Technologies, 2019, vol. 1: 4171-4186.
  2. Luca, Michael, and Georgios Zervas. "Fake it Till You Make it: Reputation, Competition, and Yelp Review Fraud." Management Science, 2016, vol. 62, no. 12: 3412-3427.
  3. Lundberg, Scott M., and Su-In Lee. "A Unified Approach to Interpreting Model Predictions." Advances in Neural Information Processing Systems, 2017, vol. 30: 1-10.
  4. Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. " Why Should I Trust you? Explaining the Predictions of Any Classifier." In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 135-1144.
  5. Abedin, Ehsan, Antonette Mendoza, Pouria Akbarighatar, and Shanika Karunasekera. "Predicting Credibility of Online Reviews: an Integrated Approach." IEEE Access, 2024, vol. 12: 49050-49061.
  6. Mohawesh, Rami, Shuxiang Xu, Matthew Springer, Yaser Jararweh, Muna Al-Hawawreh, and Sumbal Maqsood. "An Explainable Ensemble of Multi-View Deep Learning Model for Fake Review Detection." Journal of King Saud University Computer and Information Sciences, 2023, vol. 35, no. 8: 101644.
  7. Wang, Qiang, Wen Zhang, Jian Li, and Zhenzhong Ma. "Complements or Confounders? A Study of Effects of Target and Non-Target Features on Online Fraudulent Reviewer Detection." Journal of Business Research, 2023, vol. 167: 114200.
  8. Mohawesh, Rami, Haythem Bany Salameh, Yaser Jararweh, Mohannad Alkhalaileh, and Sumbal Maqsood. "Fake Review Detection using Transformer-Based Enhanced LSTM and Roberta." International Journal of Cognitive Computing in Engineering, 2024, vol. 5: 250-258.
  9. Das, Ronnie, Wasim Ahmed, Kshitij Sharma, Mariann Hardey, Yogesh K. Dwivedi, Ziqi Zhang, Chrysostomos Apostolidis, and Raffaele Filieri. " Towards The Development of an Explainable E-Commerce Fake Review Index: An Attribute Analytics Approach." European Journal of Operational Research, 2024, vol. 317, no. 2: 382-400.
  10. Liu, Jinhao, Pei Quan, and Wen Zhang. "A Study on Fake Review Detection Based on Roberta and Behavioral Features." Procedia Computer Science, 2024, vol. 242: 1323-1330.
  11. Kaggle, “Amazon Product Reviews Dataset,” https://www.kaggle.com/datasets/yasserh/amazon-product-reviews-dataset