Detecting Coordinated Fake Review Campaigns Using Graph-Based Behavioral Analysis
Keywords:
Fake Review Detection, E-Commerce, Graph Neural Networks (GNN), Behavioral Analysis, Anomaly Detection, Coordinated Campaigns, Fraud Detection, Machine LearningAbstract
The rapid growth of AI-driven e-commerce platforms has significantly increased the reliance on online reviews for consumer decision-making, thereby making these platforms highly susceptible to manipulation through coordinated fake review campaigns. This study proposes a novel graph-based behavioral analysis framework to detect such campaigns by modeling the complex relationships among users, products, and reviews as a heterogeneous graph. The proposed approach integrates structural, behavioral, and temporal features within a Graph Neural Network (GNN) architecture to effectively capture coordinated patterns and anomalous interactions. Furthermore, an anomaly detection mechanism is incorporated to enhance the identification of suspicious nodes and clusters. Experimental evaluation demonstrates that the proposed model outperforms traditional machine learning and deep learning approaches in terms of accuracy, precision, recall, and F1-score. The results highlight the effectiveness of multi-dimensional feature integration and graph-based learning in uncovering dense subgraphs associated with fraudulent activities. Additionally, visualization techniques improve the interpretability of the model, enabling practical deployment in real-world e-commerce systems. Despite certain limitations related to scalability and dynamic adaptation, the framework provides a robust and scalable solution for detecting coordinated fake review campaigns. The findings contribute to enhancing trust, transparency, and security in modern e-commerce ecosystems and offer promising directions for future research in explainable and real-time fraud detection systems.
Downloads
References
X. Hu et al., "Cost-sensitive GNN-based imbalanced learning for mobile social network fraud detection," IEEE Transactions on Computational Social Systems, vol. 11, no. 2, pp. 2675-2690, 2023.
A. S. Shethiya, "Deploying AI Models in. NET Web Applications Using Azure Kubernetes Service (AKS)," Spectrum of Research, vol. 5, no. 1, 2025.
S. M. Abd-Alhalem, H. A. Ali, N. F. Soliman, A. D. Algarni, and H. S. Marie, "Advancing e-commerce authenticity: A novel fusion approach based on deep learning and aspect features for detecting false reviews," IEEE Access, vol. 12, pp. 116055-116070, 2024.
N. Cao, S. Ji, D. K. Chiu, and M. Gong, "A deceptive reviews detection model: Separated training of multi-feature learning and classification," Expert Systems with Applications, vol. 187, p. 115977, 2022.
R. Mohawesh, H. B. Salameh, Y. Jararweh, M. Alkhalaileh, and S. Maqsood, "Fake review detection using transformer-based enhanced LSTM and RoBERTa," International Journal of Cognitive Computing in Engineering, vol. 5, pp. 250-258, 2024.
J. Zhao, M. Shao, H. Tang, J. Liu, L. Du, and H. Wang, "RHGNN: Fake reviewer detection based on reinforced heterogeneous graph neural networks," Knowledge-Based Systems, vol. 280, p. 111029, 2023.
Y. Vitulyova, T. Babenko, K. Kolesnikova, N. Kiktev, and O. Abramkina, "A Hybrid Approach Using Graph Neural Networks and LSTM for Attack Vector Reconstruction," Computers, vol. 14, no. 8, p. 301, 2025.
Y. Liu, Z. Sun, and W. Zhang, "Improving fraud detection via hierarchical attention-based graph neural network," Journal of Information Security and Applications, vol. 72, p. 103399, 2023.
Y. Xu et al., "Time-aware graph embedding: A temporal smoothness and task-oriented approach," ACM Transactions on Knowledge Discovery from Data (TKDD), vol. 16, no. 3, pp. 1-23, 2021.
