Marketing and Management of Innovations

ISSN (print) – 2218-4511 

ISSN (online) – 2227-6718

Registered in the Media Registrants-Register

Identifier in the register: R30-01179 Decision dated August 31, 2023, No. 759

The language of publication is English. 

Issued 4 times a year (March, June, September, December) since 2010

Business Model: Golden Open Access | APC Policy

Publisher & Founder:

logo_longENG

Editor-in-Chieff             View Editorial Board

Oleksii Lyulyov

Sumy State University | Ukraine

Sentiment Analysis as an Innovation in Inflation Forecasting in Romania

Mihaela Simionescu 1,2,3,*,  , Alexandru-Sabin Nicula 2,4,  
  1. Faculty of Business and Administration, University of Bucharest, Bucharest, Romania
  2. Academy of Romanian Scientists, Bucharest, Romania
  3. Institute for Economic Forecasting, Romanian Academy, Bucharest, Romania
  4. National Institute for Economic Research “Costin C. Kirițescu”, Romanian Academy, Bucharest, Romania

     * Corresponding author

DOI: https://doi.org/10.21272/mmi.2024.2-02

Pages: 13-25

Received: 10 January 2024

Revised: 13 May 2024

Accepted: 14 June 2024

Abstract

Romania faced the highest inflation rate in the European Union at the beginning of 2024, but progress has been made compared to that in 2023 due to the increasing interest rate. This inflation stemmed from a combination of global and domestic factors (global factors such as the Russia-Ukraine war, supply chain disruptions caused by the COVID-19 pandemic and war, rising commodity prices, domestic factors such as wage and pension increases, tax and charge hikes, and a strategy of gradual increase in the monetary policy interest rate). The National Bank of Romania (NBR) uses a combination of monetary policy instruments to target inflation and provides quarterly forecasts. However, under uncertain conditions, numerical forecasts are less reliable, and the inclusion of sentiment analysis in forecasts might lead to innovation in the field by improving the prediction accuracy. Sentiment analysis has become increasingly important in the field of economics, offering valuable insights and potentially improving economic forecasting and decision-making due to rapid technological progress. Sentiment analysis can identify potential changes in consumer behaviour and business decisions before they are translated into actual economic data, providing an early warning system for economic trends and potential crises. The methodological background relies on natural language processing to extract sentiment indices for large amounts of texts in Inflation Reports provided by NBR. Moreover, the sentiment indices calculated by IntelliDocker are incorporated into autoregressive distributed lag (ARDL) models to provide quarterly inflation forecasts. This type of econometric model has the advantage of addressing endogeneity. Moreover, the unemployment rate is considered an inflation predictor since tensions in the labour market might impact inflation. This paper contributes to empirical forecasting by proposing sentiment forecasts that are more accurate than NBR numerical forecasts corresponding to the 2006: Q1-2023: Q4 horizon. The new forecasting method might be used to make inflation predictions for the next quarters. More accurate forecasts would be valuable for businesses, the central bank, policymakers, and the general public. However, while sentiment analysis offers valuable insights, it is important to remember that human judgment and expertise remain essential for interpreting the data and making informed economic decisions.

Keywords: inflation; forecasts; sentiment index; natural language processing.

How to Cite: Simionescu, M., & Nicula, A. S. (2024). Sentiment Analysis as Innovation in the Inflation Forecasting in Romania. Marketing and Management of Innovations, 15(2), 13–25. https://doi.org/10.21272/mmi.2024.2-02

Abstract Views

PDF Downloads

ccbyThis work is licensed under a Creative Commons Attribution 4.0 International License

References

  1. Angeletos, G. M., Collard, F., & Dellas, H. (2018). Quantifying confidence. Econometrica, 86(5), 1689–1726. [Google Scholar] [CrossRef]
  2. Angeletos, G. M., & La’o, J. (2013). Sentiments. Econometrica, 81(2), 739-779. [Google Scholar] [CrossRef]
  3. Ardia, D., Bluteau, K., Borms, S., & Boudt, K. (2020). Econometrics meets sentiment: an overview of methodology and applications. Journal of Economic Survey, 34(3), 512–547. [Google Scholar] [CrossRef]
  4. Ardia, D., Bluteau, K., Borms, S., & Boudt, K. (2021). The R package sentometrics to compute, aggregate and predict with textual sentiment. Journal of Statistical Software, 99(2), 1–40. [Google Scholar] [CrossRef]
  5. Ardia, D., Bluteau, K., & Boudt, K. (2019). Questioning the news about economic growth: Sparse forecasting using thousands of news-based sentiment values. International Journal of Forecasting, 35(4), 1370–1386. [Google Scholar] [CrossRef]
  6. Baciu, I. C. (2015). Stochastic models for forecasting inflation rate. Empirical evidence from Romania. Procedia Economics and Finance, 20, 44-52. [Google Scholar] [CrossRef]
  7. Bajo, E., & Raimondo, C. (2017). Media sentiment and IPO underpricing. Journal of Corporate Finance, 46, 139–153. [Google Scholar][CrossRef]
  8. Baker, S. R., Bloom, N., & Davis, S. J. (2016). Measuring economic policy uncertainty. The quarterly journal of economics, 131(4), 1593–1636. [Google Scholar] [CrossRef]
  9. Bortoli, C., Combes, S., & Renault, T. (2018). Nowcasting GDP growth by reading newspapers. Economie et Statistique, 505(1), 17–33. [Google Scholar]
  10. Cambria, E., Das, D., Bandyopadhyay, S., & Feraco, A. (2017). Affective computing and sentiment analysis. A practical guide to sentiment analysis, 1–10. [Google Scholar] [CrossRef]
  11. Casey, G. P., & Owen, A. L. (2013). Good news, bad news, and consumer confidence. Social Science Quarterly, 94(1), 292–315. [Google Scholar] [CrossRef]
  12. Castle, J. L., Hendry, D. F., & Martinez, A. B. (2017). Evaluating forecasts, narratives and policy using a test of invariance. Econometrics, 5(3), Article 39. [Google Scholar] [CrossRef]
  13. Clements, M. P., & Reade, J. J. (2020). Forecasting and forecast narratives: The Bank of England inflation reports. International Journal of Forecasting, 36(4), 1488–1500. [Google Scholar] [CrossRef]
  14. Di Fatta, G., Reade, J. J., Jaworska, S., & Nanda, A. (2015). Big social data and political sentiment: the tweet stream during the UK general election 2015 campaign. In 2015 IEEE international conference on smart city/socialcom/sustaincom (smartcity)(pp. 293-298). IEEE. [Google Scholar] [CrossRef]
  15. Ericsson, N. R. (2016). Eliciting GDP forecasts from the FOMC’s minutes around the financial crisis. International Journal of Forecasting, 32(2), 571–583. [Google Scholar] [CrossRef]
  16. Eugster, P., & Uhl, M. W. (2024). Forecasting inflation using sentiment. Economics Letters, Article 111575. [Google Scholar] [CrossRef]
  17. Eurostat (2024). Annual inflation down to 2.8% in the euro area. [Link]
  18. Evans, J. A., & Aceves, P. (2016). Machine translation: Mining text for social theory. Annual review of sociology, 42, 21–50. [Google Scholar][CrossRef]
  19. Feldman, R., Govindaraj, S., Livnat, J., & Segal, B. (2010). Management’s tone change, post earnings announcement drift and accruals. Review of Accounting Studies, 15, 915–953. [Google Scholar] [CrossRef]
  20. Folgieri, R., Baldigara, T., & Mamula, M. (2018). Sentiment analysis and artificial neural networks-based econometric models for tourism demand forecasting. In Tourism & Hospitality Industry: Conference Proceedings(pp. 88-97). Tourism and Hospitality Industry. [Google Scholar]
  21. Fraiberger, S. P. (2016). News sentiment and cross-country fluctuations. Proceedings of the First Workshop on NLP and Computational Social Science, 125–131. [Google Scholar] [CrossRef]
  22. Garcia, D. (2013). Sentiment during recessions. The journal of finance, 68(3), 1267–1300. [Google Scholar] [CrossRef]
  23. Grimmer, J., & Stewart, B. M. (2013). Text as data: The promise and pitfalls of automatic content analysis methods for political texts. Political analysis, 21(3), 267–297. [Google Scholar] [CrossRef]
  24. Hansen, S., & McMahon, M. (2016). Shocking language: Understanding the macroeconomic effects of central bank communication. Journal of International Economics, 99, 114–133. [Google Scholar] [CrossRef]
  25. Henry, E. (2008). Are investors influenced by how earnings press releases are written?. The Journal of Business Communication (1973), 45(4), 363–407. [Google Scholar] [CrossRef]
  26. Hussein, D. M. E. D. M. (2018). A survey on sentiment analysis challenges. Journal of King Saud University-Engineering Sciences, 30(4), 330–338. [Google Scholar] [CrossRef]
  27. Jegadeesh, N., & Wu, D. (2013). Word power: A new approach for content analysis. Journal of financial economics, 110(3), 712–729. [Google Scholar] [CrossRef]
  28. Jones, J. T., Sinclair, T. M., & Stekler, H. O. (2020). A textual analysis of Bank of England growth forecasts. International Journal of Forecasting, 36(4), 1478–1487. [Google Scholar] [CrossRef]
  29. Kearney, C., & Liu, S. (2014). Textual sentiment in finance: A survey of methods and models. International Review of Financial Analysis, 33, 171–185. [Google Scholar] [CrossRef]
  30. Kräussl, R., & Mirgorodskaya, E. (2017). Media, sentiment and market performance in the long run. The European Journal of Finance, 23(11), 1059–1082. [Google Scholar] [CrossRef]
  31. Liang, B., Su, H., Gui, L., Cambria, E., & Xu, R. (2022). Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems, 235, Article 107643. [Google Scholar] [CrossRef]
  32. Ludvigson, S. C. (2004). Consumer confidence and consumer spending. Journal of Economic perspectives, 18(2), 29–50. [Google Scholar][CrossRef]
  33. Lukauskas, M., Pilinkienė, V., Bruneckienė, J., Stundžienė, A., Grybauskas, A., & Ruzgas, T. (2022). Economic activity forecasting based on the sentiment analysis of news. Mathematics, 10(19), 3461. [Google Scholar] [CrossRef]
  34. Munezero, M., Montero, C. S., Sutinen, E., & Pajunen, J. (2014). Are they different? Affect, feeling, emotion, sentiment, and opinion detection in text. IEEE transactions on affective computing, 5(2), 101–111. [Google Scholar] [CrossRef]
  35. NBR- National Bank of Romania (2024). Inflation Reports. [Link]
  36. Nyman, R., Kapadia, S., & Tuckett, D. (2021). News and narratives in financial systems: exploiting big data for systemic risk assessment. Journal of Economic Dynamics and Control, 127, Article 104119. [Google Scholar] [CrossRef]
  37. Petropoulos, F., Apiletti, D., Assimakopoulos, V., Babai, M. Z., Barrow, D. K., Taieb, S. B., … & Ziel, F. (2022). Forecasting: theory and practice. International Journal of Forecasting, 38(3), 705–871. [Google Scholar] [CrossRef]
  38. Romer, C. D., & Romer, D. H. (2008). The FOMC versus the staff: where can monetary policymakers add value?. American Economic Review, 98(2), 230–235. [Google Scholar] [CrossRef]
  39. Shapiro, A. H., Sudhof, M., & Wilson, D. J. (2022). Measuring news sentiment. Journal of econometrics, 228(2), 221–243. [Google Scholar][CrossRef]
  40. Sharpe, S. A., Sinha, N. R., & Hollrah, C. A. (2023). The power of narrative sentiment in economic forecasts. International Journal of Forecasting, 39(3), 1097–1121. [Google Scholar] [CrossRef]
  41. Simionescu, M. (2020). Bayesian combined forecasts and Monte Carlo simulations to improve inflation rate predictions in Romania. Research Papers in Economics and Finance, 4(1), 7–20. [Google Scholar]
  42. Simionescu, M. (2022). Econometrics of sentiments-sentometrics and machine learning: the improvement of inflation predictions in Romania using sentiment analysis. Technological Forecasting and Social Change, 182, Article 121867. [Google Scholar] [CrossRef]
  43. Stekler, H., & Symington, H. (2016). Evaluating qualitative forecasts: The FOMC minutes, 2006–2010. International Journal of Forecasting, 32(2), 559–570. [Google Scholar] [CrossRef]
  44. Susskind, Z., Arden, B., John, L. K., Stockton, P., & John, E. B. (2021). Neuro-symbolic ai: An emerging class of ai workloads and their characterization. arXiv preprint arXiv:2109.06133. [Google Scholar] [CrossRef]
  45. Taboada, M. (2016). Sentiment analysis: An overview from linguistics. Annual Review of Linguistics, 2, 325–347. [Google Scholar][CrossRef]
  46. Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of finance, 62(3), 1139–1168. [Google Scholar] [CrossRef]
  47. Thorsrud, L. A. (2020). Words are the new numbers: A newsy coincident index of the business cycle. Journal of Business & Economic Statistics, 38(2), 393–409. [Google Scholar] [CrossRef]
  48. Van de Kauter, M., Desmet, B., & Hoste, V. (2015). The good, the bad and the implicit: a comprehensive approach to annotating explicit and implicit sentiment. Language resources and evaluation, 49, 685–720. [Google Scholar] [CrossRef]
  49. Wang, W., Guo, L., & Wu, Y. J. (2022a). The merits of a sentiment analysis of antecedent comments for the prediction of online fundraising outcomes. Technological Forecasting and Social Change, 174, Article 121070. [Google Scholar] [CrossRef]
  50. Wang, Y., Song, W., Tao, W., Liotta, A., Yang, D., Li, X., … & Zhang, W. (2022b). A systematic review on affective computing: Emotion models, databases, and recent advances. Information Fusion, 83, 19–52. [Google Scholar] [CrossRef]
  51. Zhang, L., Wang, S., & Liu, B. (2018). Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), Article e1253. [Google Scholar] [CrossRef]

View articles in other formats

License

ccby This work is licensed under a Creative Commons Attribution 4.0 International License

Coyright

Copyright (c) 2024 The Author(s).

Published by Sumy State University

Issue

Contacts

Sumy State University
116, Kharkivska st., 40007 Sumy, Ukraine

e-mail: mmi@fem.sumdu.edu.ua

About us

About publisher Sumy State University

Journal’s history

Advertising 

Follow us

LinkedIn

Twitter

 

Company 2023 © Sumy State University