A Review of Social Media Sentiment Analysis in Financial Risk Control: Based on Natural Language Processing Technologies
Main Article Content
Keywords
natural language processing (NLP), social media sentiment analysis, financial risk control, pre-trained language models, credit risk control
Abstract
This review examines the application of social media sentiment analysis, driven by Natural Language Processing (NLP) technologies, within financial risk control. It outlines the four-stage evolution of NLP, from traditional methods to pre-trained models. Using credit risk control as an example, it elaborates on its application across the entire loan lifecycle: pre-loan, in-loan, and post-loan. The study identifies limitations such as data scarcity, insufficient model generalization and interpretability, and high implementation costs. It also explores potential breakthroughs, including dataset construction and model optimization, aiming to provide a framework for related research and practice.
References
- Ardekani, A. M., Bertz, J., Bryce, C., Dowling, M. and Long, S. C., (2024). FinSentGPT: A universal financial sentiment engine? International Review of Financial Analysis, vol. 94, p. 103291.
- Bollen, J., Mao, H. and Zeng, X., (2011). Twitter mood predicts the stock market. Journal of computational science, vol. 2, no. 1, pp. 1-8.
- Cao, S. S., (2024). Stock Comment Sentiment Analysis Based on Baichuan LLM and LoRA. Master's Thesis, Southwestern University of Finance and Economics.
- Du, K., Zhao, Y., Mao, R., Xing, F. and Cambria, E., (2025). Natural language processing in finance: A survey. Information Fusion, vol. 115, p. 102755.
- Duan, W. C. and Xue, T., (2024). FinBERT-RCNN-ATTACK: Emotional analysis model of financial text. Computer Technology and Development, vol. 34, no. 5, pp. 157-162.
- Lin, J. H. and Sun, L. X., (2025). Text analysis in economics and finance with large language models: Fundamentals, applications,and future prospects. China Journal of Econometrics, vol. 5, no. 1, pp. 1-34.
- Liu, Z., Wu, X. and Yao, W., (2024). Published. Social Media Analysis: The Relationship Between Private Investors and Stock Price. Machine Learning, Optimization, and Data Science. LOD 2023, Cham. Springer Nature Switzerland, pp. 45-54.
- Loughran, T. and McDonald, B., (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of finance, vol. 66, no. 1, pp. 35-65.
- Lu, J. P., (2025). Research on Sentiment Analysis of Listed Companies' Annual Reports Based on Natural Language Processing Technology. Master's Thesis, Civil Aviation Flight University of China.
- Nasiopoulos, D. K., Roumeliotis, K. I., Sakas, D. P., Toudas, K. and Reklitis, P., (2025). Financial Sentiment Analysis and Classification: A Comparative Study of Fine-Tuned Deep Learning Models. International Journal of Financial Studies, vol. 13, no. 2, p. 75.
- Sheetal, R. and Aithal, P. K., (2025). Enhancing Financial Sentiment Analysis: Integrating the LoughranMcDonald Dictionary with BERT for Advanced Market Predictive Insights. Procedia Computer Science, vol. 258, pp. 2244-2257.
- Todd, A., Bowden, J. and Moshfeghi, Y., (2024). Text‐based sentiment analysis in finance: Synthesising the existing literature and exploring future directions. Intelligent Systems in Accounting, Finance and Management, vol. 31, no. 1, p. e1549.
- Xiao, J., Wang, L., Yang, Y. J., Li, N., Zhao, M. M., Chen, Y. X. and Tan, T., (2021). A systematic review of perceptual cognitive technology and its application in the field of financial risk early warning. CAAI Transactions on Intelligent Systems, vol. 16, no. 05, pp. 941-961.
- Xu, Q. R., Zhu, P., Luo, Y. F. and Dong, Q. W., (2021). Research progress in Chinese named entity recognition in the financial field. Journal of East China Normal University (Natural Science), vol. 5, pp. 1-13.
- Zhou, Z., Chen, Z., Zhang, Y., Lu, T. and Lu, X., (2025). Social media meets FinTech platforms: How do online emotions support credit risk decision-making? Decision Support Systems, vol. 195, p. 114471.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.