Artificial Intelligence-Based Sentiment Analysis of Indian Union Budget Speeches Using Finbert: Evidence from Selected Indian Information Technology Companies

Government budget speeches play a vital role in communicating fiscal priorities, economic reforms, and policy directions that shape business expectations across industries. In recent years, advances in Artificial Intelligence (AI) and Natural Language Processing (NLP) have created new opportunities to evaluate such policy documents using data-driven approaches rather than relying solely on qualitative interpretation. Although several studies have explored sentiment analysis in financial news and corporate disclosures, limited attention has been given to analysing Indian Union Budget speeches using finance-specific language models and examining their relationship with corporate financial performance. This study investigates the sentiment expressed in six Indian Union Budget speeches covering the financial years 2021–22 to 2026–27 and evaluates whether policy sentiment is associated with the financial performance of selected Indian Information Technology (IT) companies. The study employs FinBERT as the primary sentiment-analysis model, while VADER and TextBlob are used as complementary techniques for comparison. Financial performance is assessed using secondary data on revenue, operating profit, and net profit for five leading Indian IT companies: Infosys, Tata Consultancy Services (TCS), Wipro, HCL Technologies, and Tech Mahindra. Pearson correlation analysis is applied to examine the relationship between sentiment scores and financial indicators. The findings indicate that Union Budget speeches generally exhibit a positive policy sentiment across the study period, with noticeable variations in sentiment intensity between financial years. However, correlation analysis suggests that the relationship between budget sentiment and company-level financial performance is generally weak and statistically insignificant for most financial indicators. These results imply that while fiscal policy communication contributes to the broader economic environment, the long-term financial performance of large Indian IT firms is influenced more strongly by international demand, digital transformation, technological innovation, exchange-rate movements, and firm-specific strategic decisions than by domestic budget sentiment alone. The study contributes to the growing literature on AI-enabled financial analysis by demonstrating the application of FinBERT to government policy documents and by integrating sentiment analysis with financial performance evaluation. The findings also provide useful insights for policymakers, financial analysts, corporate managers, and researchers interested in applying AI-based text analytics to economic policy assessment.

Artificial Intelligence, FinBERT, Natural Language Processing, Sentiment Analysis, Indian Union Budget, Financial Performance

1. Anica-Popa, I. F., Vrîncianu, M., Anica-Popa, L. E., Cișmașu, I. D., & Tudor, C. G. (2024). Generative AI in accounting and audit. Electronics, 13(13), 2621. [Google Scholar] [Crossref]

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

3. Bahoo, S., Cucculelli, M., Goga, X., & Mondolo, J. (2024). Artificial intelligence in finance: A comprehensive review through bibliometric and content analysis. SN Business & Economics, 4(2), 23. [Google Scholar] [Crossref]

4. Baker, S. R., Bloom, N., & Davis, S. J. (2016). Measuring economic policy uncertainty. Quarterly Journal of Economics, 131(4), 1593–1636. [Google Scholar] [Crossref]

5. Bayakhmetova, A., Rudenko, L., Krylova, L., Suleimenova, B., Niyazbekova, S., & Nurpeisova, A. (2025). Artificial intelligence in financial behavior: Bibliometric ideas and new opportunities. Journal of Risk and Financial Management, 18(3), 159. [Google Scholar] [Crossref]

6. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8. [Google Scholar] [Crossref]

7. Brown, N. C., Crowley, R. M., & Elliott, W. B. (2020). Textual analysis in accounting and finance: A survey. The Accounting Review. [Google Scholar] [Crossref]

8. Cao, L. (2022). AI in finance: Challenges, techniques, and opportunities. ACM Computing Surveys. [Google Scholar] [Crossref]

9. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). [Google Scholar] [Crossref]

10. Dowling, M., & Lucey, B. (2023). ChatGPT for finance research. Finance Research Letters, 56. [Google Scholar] [Crossref]

11. Faheem, M., et al. (2024). Enhancing financial forecasting accuracy through AI-driven predictive analytics models. [Google Scholar] [Crossref]

12. Gentzkow, M., Kelly, B., & Taddy, M. (2019). Text as data. Journal of Economic Literature, 57(3), 535–574. [Google Scholar] [Crossref]

13. Giudici, P., & Raffinetti, E. (2023). SAFE artificial intelligence in finance. Finance Research Letters, 56, 104088. [Google Scholar] [Crossref]

14. Gupta, R., & Sharma, V. (2024). AI and NLP applications in financial sentiment analysis for economic policy evaluation. Risks, 12(4), 56. [Google Scholar] [Crossref]

15. Huang, A., Wang, H., & Yang, Y. (2023). FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Research. [Google Scholar] [Crossref]

16. Jain, V., & Kulkarni, P. A. (2023). Integrating AI techniques for enhanced financial forecasting and budgeting strategies. International Journal of Economics and Management Studies, 10(9), 9–15. [Google Scholar] [Crossref]

17. Jegadeesh, N., & Wu, D. (2013). Word power: A new approach for content analysis. Journal of Financial Economics. [Google Scholar] [Crossref]

18. Karanikola, A., et al. (2023). Financial sentiment analysis: Classic methods vs. deep learning models. [Google Scholar] [Crossref]

19. Kearney, C., & Liu, S. (2014). Textual sentiment in finance: A survey of methods and models. Journal of Behavioral Finance, 15(2), 171–185. [Google Scholar] [Crossref]

20. Kumar, A., et al. (2024). Words that move markets. [Google Scholar] [Crossref]

21. Li, F. (2010). The information content of forward-looking statements in corporate filings. Journal of Accounting Research. [Google Scholar] [Crossref]

22. Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks. Journal of Finance, 66(1), 35–65. [Google Scholar] [Crossref]

23. Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). The M4 competition: Results, findings, conclusion and way forward. International Journal of Forecasting, 34(4), 802–808. [Google Scholar] [Crossref]

24. Mishra, A., et al. (2025). Impact of Union Budget announcements on the Indian stock market. [Google Scholar] [Crossref]

25. Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., & Ngo, D. C. L. (2014). Text mining for market prediction: A systematic review. Expert Systems with Applications, 41(16), 7653–7670. [Google Scholar] [Crossref]

26. Parghi, V. K., & Zala, D. (2025). Determinants of financial performance in Indian financial services companies. [Google Scholar] [Crossref]

27. Rane, N., et al. (2023). Leading-edge AI-powered financial forecasting. [Google Scholar] [Crossref]

28. Sharma, S. (2023). Artificial intelligence in financial forecasting: Evidence from literature. AIP Conference Proceedings. [Google Scholar] [Crossref]

29. Shen, Y., & Zhang, P. (2024). Financial sentiment analysis on news and reports using large language models and FinBERT. arXiv. [Google Scholar] [Crossref]

30. Singh, A., et al. (2025). What do sentiments of budget speeches mean for stock returns? Economic Modelling. [Google Scholar] [Crossref]

31. Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. Journal of Finance, 62(3), 1139–1168. [Google Scholar] [Crossref]

32. Wasserbacher, M., & Spindler, M. (2022). Machine learning for financial forecasting, planning and analysis. Digital Finance. [Google Scholar] [Crossref]

33. Zhu, E., et al. (2024). BERTopic-driven stock market predictions: Unraveling sentiment insights. [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition