A Robust Rating Prediction Model for Recommendation Systems Based on Fake User Detection and Multi-Layer Feature Fusion
), Abstract
The effectiveness of recommendation systems heavily relies on accurately predicting user ratings for items based on user preferences and item attributes derived from ratings and reviews. However, the increasing presence of fake user data in these ratings and reviews poses significant challenges, hindering feature extraction, diminishing rating prediction accuracy, and eroding user trust in the system. To tackle this issue, we propose a robust rating prediction model for recommendation systems that integrates fake user detection and multi-layer feature fusion. Our model utilizes a GraphSAGE-based submodel to filter out fake user data from rating data and review texts. To strengthen fake user detection, we enhance GraphSAGE by selecting aggregation neighbors based on the collusion fraud degree among users, and employ an attention mechanism to weigh the contribution of each neighbor during representation aggregation. Furthermore, we introduce a multi-layer feature fusion submodel to integrate diverse features extracted from the filtered ratings and reviews. For deep feature extraction from review texts, we implement a temporal attention mechanism to analyze the relevance of reviews over time. For shallow feature extraction from rating data, we incorporate trust evaluation mechanism and cloud model to assess the influence of trusted neighbors’ ratings. In our evaluation, we compare our model against six baseline models for fake user detection and four rating prediction models across five datasets. The results demonstrate that our model exhibits significant performance advantages in both fake user detection and rating prediction.
Keywords
References
V. Deshpande and P. K. Pendem, Logistics performance, ratings, and its impact on customer purchasing behavior and sales in E-commerce platforms, Manuf. Serv. Oper. Manag., vol. 25, no. 3, pp. 827–845, 2023.
C. Changchit, T. Klaus, and R. Lonkani, Online reviews: What drives consumers to use them, J. Comput. Inf. Syst., vol. 62, no. 2, pp. 227–236, 2022.
M. Si and Q. Li, Shilling attacks against collaborative recommender systems: a review, Artif. Intell. Rev., vol. 53, no. 1, pp. 291–319, 2020.
L. Sang, M. Xu, S. Qian, and X. Wu, Adversarial heterogeneous graph neural network for robust recommendation, IEEE Trans. Comput. Soc. Syst., vol. 10, no. 5, pp. 2660–2671, 2023.
X. Ran, Y. Wang, L. Y. Zhang, and J. Ma, A differentially private nonnegative matrix factorization for recommender system, Inf. Sci., vol. 592, pp. 21–35, 2022.
S. Zhang, L. Yao, A. Sun, and Y. Tay, Deep learning based recommender system, ACM Comput. Surv., vol. 52, no. 1, pp. 1–38, 2020.
X. Feng and Y. Zeng, Joint deep modeling of rating matrix and reviews for recommendation, (in Chinese), Chinese Journal of Computers, vol. 43, no. 5, pp. 884–900, 2020.
S. Li, L. Yu, and X. Deng, Recommendation model combining deep sentiment analysis and scoring matrix, (in Chinese), Journal of Electronics & Information Technology, vol. 44, no. 1, pp. 245–253, 2022.
Y. Xu and F. Zhang, Detecting shilling attacks in social recommender systems based on time series analysis and trust features, Knowl. Based Syst., vol. 178, pp. 25–47, 2019.
F. Zhang and S. Wang, Detecting Group shilling attacks in online recommender systems based on bisecting K-means clustering, IEEE Trans. Comput. Soc. Syst., vol. 7, no. 5, pp. 1189–1199, 2020.
C. Tong, X. Yin, J. Li, T. Zhu, R. Lv, L. Sun, and J. J. P. C. Rodrigues, A shilling attack detector based on convolutional neural network for collaborative recommender system in social aware network, Comput. J., vol. 61, no. 7, pp. 949–958, 2018.
S. Wang, P. Zhang, H. Wang, H. Yu, and F. Zhang, Detecting shilling groups in online recommender systems based on graph convolutional network, Inf. Process. Manag., vol. 59, no. 5, p. 103031, 2022.
S. Wang, P. Zhang, H. Wang, J. Chao, and F. Zhang, A shilling group detection framework based on deep learning techniques, Secur. Commun. Netw., vol. 2022, p. 2323132, 2022.
N. Deshai and B. B. Rao, Deep learning hybrid approaches to detect fake reviews and ratings, Journal of Scientific and Industrial Research, vol. 82, no. 1, pp. 120–127, 2023.
Y. Yuan, A. Zahir, and J. Yang, Modeling implicit trust in matrix factorization-based collaborative filtering, Appl. Sci., vol. 9, no. 20, p. 4378, 2019.
S. Xu, H. Zhuang, F. Sun, S. Wang, T. Wu, and J. Dong, Recommendation algorithm of probabilistic matrix factorization based on directed trust, Comput. Electr. Eng., vol. 93, p. 107206, 2021.
W.-D. Xi, L. Huang, C.-D. Wang, Y.-Y. Zheng, and J.-H. Lai, Deep rating and review neural network for item recommendation, IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 11, pp. 6726–6736, 2022.
L. Wu, X. He, X. Wang, K. Zhang, and M. Wang, A survey on accuracy-oriented neural recommendation: From collaborative filtering to information–rich recommendation, IEEE Trans. Knowl. Data Eng., vol. 35, no. 5, pp. 4425–4445, 2023.
H. Liu, Y. Wang, Q. Peng, F. Wu, L. Gan, L. Pan, and P. Jiao, Hybrid neural recommendation with joint deep representation learning of ratings and reviews, Neurocomputing, vol. 374, pp. 77–85, 2020.
S. Abinaya and K. U. Kumar, Enhancing multicriteria-based recommendations by alleviating scalability and sparsity issues using collaborative denoising autoencoder, Comput. Mater. Continua, vol. 78, no. 2, pp. 2269–2286, 2024.
X. Ma, J. Wu, S. Xue, J. Yang, C. Zhou, Q. Z. Sheng, H. Xiong, and L. Akoglu, A comprehensive survey on graph anomaly detection with deep learning, IEEE Trans. Knowl. Data Eng., vol. 35, no. 12, pp. 12012–12038, 2023.
京公网安备11010802044758号