Skip to main navigation menu Skip to main content Skip to site footer

Vol. 6 No. 1 (2025)
2025 Edition

Articles

NLP-Quantified ESG News Sentiment and Portfolio Outcomes Evidence from Real-Time Signals

Published 2025-11-14

  • Yiyi Cai

Yiyi Cai
Enterprise Risk Management, Columbia University, NY, USA

Abstract

Environmental, Social, and Governance (ESG) investing has gained unprecedented momentum in global financial markets, driving the need for sophisticated analytical frameworks that can process vast amounts of unstructured information. This research presents a comprehensive investigation into the application of natural language processing techniques for ESG news sentiment analysis and its subsequent impact on investment portfolio performance. The study develops a multi-dimensional sentiment analysis model that extracts ESG-related information from financial news sources, incorporating advanced text mining algorithms to quantify sentiment scores across environmental, social, and governance dimensions. Through empirical analysis of portfolio performance metrics, the research demo     nstrates that ESG sentiment-driven investment strategies yield superior risk-adjusted returns compared to traditional approaches. The methodology integrates real-time news processing capabilities with portfolio optimization algorithms, enabling dynamic allocation decisions based on sentiment-derived ESG signals. Experimental results indicate a 50.8% improvement in Sharpe ratio and 17.3% reduction in portfolio volatility when incorporating ESG sentiment analysis. The findings contribute to the advancement of sustainable finance technology and provide practical insights for institutional investors seeking to enhance portfolio performance through alternative data integration.

Keywords

ESG investing, sentiment analysis, natural language processing, portfolio optimization

View PDF

References

  1. Cao, E., & Sun, Y. (2023, December). A Data-Driven Analytical Framework for ESG-based Stock Investment Analytics using Machine Learning and Natural Language Processing. In Proceedings of the 2023 12th International Conference on Networks, Communication and Computing (pp. 225-232).
  2. Kim, M., Kang, J., Jeon, I., Lee, J., Park, J., Youm, S., ... & Moon, J. (2024). Differential Impacts of Environmental, Social, and Governance News Sentiment on Corporate Financial Performance in the Global Market: An Analysis of Dynamic Industries Using Advanced Natural Language Processing Models. Electronics, 13(22), 4507.
  3. Zeidan, R. (2022). Why don't asset managers accelerate ESG investing? A sentiment analysis based on 13,000 messages from finance professionals. Business Strategy and the Environment, 31(7), 3028-3039.
  4. Zhang, M., Shen, Q., Zhao, Z., Wang, S., & Huang, G. Q. (2025). Optimizing ESG reporting: Innovating with E-BERT models in nature language processing. Expert systems with applications, 265, 125931.
  5. Jaiswal, R., Gupta, S., & Tiwari, A. K. (2024). Decoding mood of the Twitterverse on ESG investing: opinion mining and key themes using machine learning. Management Research Review, 47(8), 1221-1252.
  6. Fischbach, J., Adam, M., Dzhagatspanyan, V., Mendez, D., Frattini, J., Kosenkov, O., & Elahidoost, P. (2023, December). Automatic eSG assessment of companies by mining and evaluating media coverage data: NLP approach and tool. In 2023 IEEE International Conference on Big Data (BigData) (pp. 2823-2830). IEEE.
  7. Goutte, S., Liu, F., Le, H. V., & Mettenheim, H. J. V. (2023). ESG Investing: A Sentiment Analysis Approach. Available at SSRN 4316107.
  8. Babaeva, M. (2024). A Study on Quantifying ESG Alpha as an access return on portfolio using ESG Sentiment in the Banking Sector with an Automated Machine Learning Approach.
  9. Andrikogiannopoulou, A., Krueger, P., Mitali, S. F., & Papakonstantinou, F. (2022). Discretionary information in ESG investing: A text analysis of mutual fund prospectuses. Available at SSRN 4082263.
  10. Zhang, Y. (2023). ESG-Based Market Risk Prediction and Management Using Machine Learning and Natural Language Processing.
  11. Jatowt, A. (2022). Predicting ESG Scores from News Articles using Natural Language Processing (Doctoral dissertation, University of Innsbruck).
  12. Wang, M., & Zhu, L. (2024). Linguistic Analysis of Verb Tense Usage Patterns in Computer Science Paper Abstracts. Academia Nexus Journal, 3(3).
  13. Liu, W., Qian, K., & Zhou, S. (2024). Algorithmic Bias Identification and Mitigation Strategies in Machine Learning-Based Credit Risk Assessment for Small and Medium Enterprises. Annals of Applied Sciences, 5(1).
  14. Mo, T., Li, P., & Jiang, Z. (2024). Comparative Analysis of Large Language Models' Performance in Identifying Different Types of Code Defects During Automated Code Review. Annals of Applied Sciences, 5(1).
  15. Xu, S. (2025). Intelligent Optimization Algorithm for Chain Restaurant Spatial Layout Based on Generative Adversarial Networks. Journal of Industrial Engineering and Applied Science, 3(3), 32-41.