Sentiment Analysis For Product Reviews : Fake Reviews Detection Using Sentiment Analysis

Overall, the detection of fake reviews has become an important issue in contemporary electronic commerce environments. The presented research has demonstrated the inefficiency of conventional sentiment analysis algorithms and stressed the importance of utilizing hybrid approaches. The application of the CNN-LSTM architecture with the use of the proposed features has shown substantial gains in the detection rates. Thus, it has been proven that the combination of various technologies is necessary to deal with sophisticated patterns of fake reviews.  

[1] A. Mukherjee, V. Venkataraman, B. Liu, and N. Glance, “Fake review detection: Classification and analysis of real and pseudo reviews,” Univ. Illinois at Chicago, Tech. Rep., 2013. [2] S. Chang, X. Zhenzhong, and G. Xuan, “Fake comment detection based on sentiment analysis,” IEEE Access, 2018. [3] F. Abri, L. F. Gutierrez, A. S. Namin, K. S. Jones, and D. R. Sears, “Fake reviews detection through analysis of linguistic features,” arXiv preprint arXiv:2010.04260, 2020. [4] J. Kumar, “Fake review detection using behavioral and contextual features,” arXiv preprint arXiv:2003.00807, 2020. [5] A. Yousif and J. Buckley, “Impact of sentiment analysis in fake review detection,” arXiv preprint arXiv:2212.08995, 2022. [6] M. J. Abd and M. H. Hussein, “Fake reviews detection in e-commerce using machine learning techniques: A comparative survey,” BIO Web Conf., 2024. [7] R. Mohawesh et al., “Fake review detection using transformer-based enhanced model,” Expert Systems with Applications, 2024. [8] J. Liu et al., “A study on fake review detection based on RoBERTa model,” Procedia Computer Science, 2024. [9] P. Sun et al., “Fake review detection model based on comment content and behavioral features,” Electronics, vol. 13, no. 21, 2024. [10] A. Gadewar et al., “Online fake review detection based on machine learning techniques,” IJSRSET, 2023.