Skip to main content

Advancing Financial Text Sentiment Analysis with Deep Learning and Ensemble Models

  • Conference paper
  • First Online:
Artificial Intelligence XLI (SGAI 2024)

Abstract

Sentiment analysis in financial text plays a crucial role in understanding market trends and predicting financial outcomes. This research investigates the impact of fine-tuning and ensemble learning techniques on the performance of Large Language Models (LLMs) for financial sentiment analysis. We focus on comparing individual fine-tuned FinBERT models and various ensemble methods, particularly stacking ensembles with different meta-learners, on the FiQA (Financial Opinion Mining and Question Answering) 2018 benchmark dataset. Our methodology involves dataset selection, model development, and rigorous evaluation using multiple metrics. The results demonstrate the effectiveness of domain-specific adaptation and the potential benefits of combining multiple models in an ensemble to improve sentiment classification performance. The stacking ensemble with a Random Forest meta-classifier achieves state-of-the-art performance on both datasets, outperforming individual fine-tuned models and other ensemble methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Malo, P., Sinha, A., Korhonen, P., Wallenius, J., Takala, P.: Good debt or bad debt: Detecting semantic orientations in economic texts. J. Assoc. Inf. Sci. Technol. 65(4), 782–796 (2014). https://doi.org/10.1002/asi.23062

    Article  Google Scholar 

  2. Araci, D.: FinBERT: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063 (2019)

  3. Xie, Q., et al.: BUFIN: a large-scale financial dataset for blockchain and DeFi research. arXiv preprint arXiv:2306.05443 (2023)

  4. Nyakurukwa, K., Seetharam, Y.: Can investor sentiment predict cryptocurrency returns? Evid. Bitcoin. Sci. Afr. 20, e01596 (2023). https://doi.org/10.1016/j.sciaf.2023.e01596

    Article  Google Scholar 

  5. Bollen, J., Mao, H., Zeng, X.: Twitter mood predicts the stock market. J. Comput. Sci. 2(1), 1–8 (2011). https://doi.org/10.1016/j.jocs.2010.12.007

    Article  Google Scholar 

  6. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)

  7. Dietterich, T.G.: Ensemble methods in machine learning. In: Kittler, J., Roli, F. (eds.) Multiple Classifier Systems. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-45014-9_1

  8. Nti, I.K., Adekoya, A.F., Weyori, B.A.: A systematic review of fundamental and technical analysis of stock market predictions. Artif. Intell. Rev. 53, 3007–3057 (2020). https://doi.org/10.1007/s10462-019-09754-z

    Article  Google Scholar 

  9. Airnow: Monthly number of active users selected leading apps that allow for online share trading worldwide from January 2017 to July 2021, by app (in 1,000s) [Graph]. Statista (2021). https://www-statista-com.manchester.idm.oclc.org/statistics/1259822/global-etrading-app-monthly-active-users/

  10. Chen, W., Li, M., Wang, X., Zou, Y.: FinGPT: instruction-following financial large language models. arXiv preprint arXiv:2310.15205 (2023)

  11. Malo, P., Sinha, A., Takala, P., Korhonen, P., Wallenius, J.: FinancialPhraseBank-v1.0 (2013). https://www.researchgate.net/publication/251231364_FinancialPhraseBank-v10

  12. Chiapudding: Kaggle Financial Sentiment. Hugging Face Datasets (2024). https://huggingface.co/datasets/chiapudding/kaggle-financial-sentiment

  13. FinanceInc: Auditor Sentiment Fine-tuned. Hugging Face Datasets (2024). https://huggingface.co/datasets/FinanceInc/auditor-sentiment-finetuned

  14. Zeroshot: Twitter Financial News Sentiment. Hugging Face Datasets (2024). https://huggingface.co/datasets/zeroshot/twitter-financial-news-sentiment

  15. Maia, M., et al.: WWW’18 open challenge: financial opinion mining and question answering. In: Companion Proceedings of the web Conference 2018, pp. 1941–1942. International World Wide Web Conferences Steering Committee, Geneva (2018). https://doi.org/10.1145/3184558.3192301

  16. Chen, Z., Shang, T., Chen, Y., Zhao, L.: FinSense: an assistant system for financial journalists and investors. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3697–3711. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.emnlp-demo.9

  17. Xie, Q., Han, W.: FinGPT: open-source financial large language models. arXiv preprint arXiv:2402.12659 (2024)

  18. Interactive Brokers: Number of accounts of Interactive Brokers from Jan 2008 to October 2021 (in 1,000s) [Graph]. Statista (2022). https://www-statista-com.manchester.idm.oclc.org/statistics/1263318/interactive-brokers-number-accounts/

  19. NVIDIA Corporation: NVIDIA Announces Financial Results for First Quarter Fiscal 2021. NVIDIA Newsroom (2020). https://nvidianews.nvidia.com/news/nvidia-announces-financial-results-for-first-quarter-fiscal-2021

  20. Sriram, K., Jin, H.: Tesla posts record quarterly deliveries after price cuts, up 4% from Q4. Reuters (2023). https://www.reuters.com/business/autos-transportation/tesla-misses-first-quarter-delivery-estimates-2023-04-02/

Download references

Acknowledgments

I would like to thank my project supervisor, Professor Sophia Ananiadou from the University of Manchester for mentoring my project as well as the researchers Jimin Huang and Qianqian Xie, leading the Fin AI group, for our discussions and helping with my understanding of the topic for this paper.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Wei Liang Russell Tang .

Editor information

Editors and Affiliations

Appendix

Appendix

Model Evaluation Python Implementation

figure a

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Tang, W.L.R. (2025). Advancing Financial Text Sentiment Analysis with Deep Learning and Ensemble Models. In: Bramer, M., Stahl, F. (eds) Artificial Intelligence XLI. SGAI 2024. Lecture Notes in Computer Science(), vol 15447. Springer, Cham. https://doi.org/10.1007/978-3-031-77918-3_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-77918-3_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-77917-6

  • Online ISBN: 978-3-031-77918-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics