Nowcasting Iran's GDP Using Sentiment Analysis of Economic News

Document Type : Research Paper

Authors

1 PhD student، Department of Economics، Faculty of Administrative Sciences and Economics، Ferdowsi University of Mashhad، Iran.

2 Assistant Professor، Department of Economics، Faculty of Administrative Sciences and Economics، Ferdowsi University of Mashhad, Iran.

3 Professor، Department of Economics، Faculty of Administrative Sciences and Economics، Ferdowsi University of Mashhad، Iran.

Abstract

This study examines textual data's ability to nowcast Iran's gross domestic product (GDP). To this end, 301,498 economic news articles from March 2005 to December 2023 were extracted from the Fars news agency website using a web crawling technique. Following initial preprocessing, the news texts were sorted into various categories via the Dirichlet Latent Allocation (LDA) model, wherein each category corresponds to a distinct news topic. Subsequently, to ascertain whether an article conveys a positive or negative sentiment, we executed lexicon-based sentiment analysis utilizing SentiStrength. Ultimately, by aggregating the news sentiment scores seasonally under each topic, we constructed a seasonal sentiment time series. These time series were then assessed for their efficacy in nowcasting Iran's quarterly GDP, employing ridge regression, lasso regression, elastic net, and gradient boosting methods. The findings reveal that incorporating textual data can reduce prediction errors by 12 to 18 percent relative to a univariate time series model. Moreover, our results suggest that sentiment extracted from textual content, particularly news articles, is a viable approach. This strategy could potentially enable the provision of immediate GDP estimates following the end of each reference quarter.

Keywords

Main Subjects

References

  1. Afshar, P. A., Manochehri, S., & Amani, R. (2023). Macroeconomic Uncertainty, Political Risk and Exchange Rate Market Fluctuations in Iran. Quarterly Journal of Applied Theories of Economics, 10(3), 67-102 (In Persian).
  2. Aghania, P., Heidari, H., & Jahangiri, Sh. (2023). Investigating the Impact of Monetary Policy Shocks on Economic Growth and Inflation in the Iranian Economy: Empirical Evidence Based on the TVP-TVP-SFAVAR-SV Model. Quarterly Journal of Applied Theories of Economics, 9(4), 61-96 (In Persian).
  3. Aguilar, P., Ghirelli, C., Pacce, M., & Urtasun, A. (2021). Can news help economic sentiment?. An application in COVID-19 times. Economics Letters, 199, 109730.
  4. Ahangari, M., Sebti, A., & Yaghoubi, M. (2023). Automatically generate lexicon for the Persian stock market. Signal and Data Processing, 20(2), 3-20 (In Persian).
  5. Algaba, A., Ardia, D., Bluteau, K., Borms, S., & Boudt, K. (2020). Econometrics meets sentiment: An overview of methodology and applications. World Bank Economic Review, 8 (3), 351-371.
  6. Angeletos, G. M., Collard, F., & Dellas, H. (2018). Quantifying confidence. Econometrica, 86(5), 1689-1726.
  7. Aprigliano, V., Emiliozzi, S., Guaitoli, G., Luciani, A., Marcucci, J., & Monteforte, L. (2023). The power of text-based indicators in forecasting Italian economic activity. International Journal of Forecasting, 39(2), 791-808.
  8. 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.
  9. Ash, E., & Hansen, S. (2023). Text algorithms in economics. Annual Review of Economics, 15(1), 659-688.
  10. Ashwin, J., Kalamara, E., & Saiz, L. (2021). Nowcasting euro area GDP with news sentiment: a tale of two crises. Journal of Applied Econometrics, 1–19.
  11. Azqueta Gavaldon, A.(2020). Text-mining in macroeconomics: the wealth of words . Doctoral dissertation, University of Glasgow.
  12. Barbaglia, L., Consoli, S., & Manzan, S. (2024). Forecasting GDP in Europe with textual data. Journal of Applied Econometrics, 39(2), 338-355.
  13. Barbaglia, L., Frattarolo, L., Onorante, L., Pericoli, F. M., Ratto, M., & Pezzoli, L. T. (2023). Testing big data in a big crisis: Nowcasting under COVID-19. International Journal of Forecasting, 39(4), 1548-1563.
  14. Blei, D. M. (2012). Probabilistic topic models.Communications of the ACM, 55(4), 77-84.
  15. Bortoli, C., Combes, S., & Renault, T. (2018). Nowcasting GDP growth by reading newspapers. Economie et Statistique, 505(1), 17-33.
  16. Brosius, A., van Elsas, E. J., & de Vreese, C. H. (2020). Bad news, declining trust? Effects of exposure to economic news on trust in the European Union. International Journal of Public Opinion Research, 32 (2): 223–242.
  17. Bybee, L., Kelly, B. T., Manela, A., & Xiu, D. (2020). The structure of economic news. Tech. rep. NBER Working paper, 26648.
  18. Coase, R. H. (1960). The problem of social cost. Law Econ, 3,1–44
  19. Eshbaugh-Soha, M. (2010). The tone of local presidential news coverage. Political Communication, 27(2), 121-140.
  20. Ferrara, L., & Simoni, A. (2023). When are Google data useful to nowcast GDP? An approach via preselection and shrinkage.Journal of Business & Economic Statistics, 41(4), 1188-1202.
  21. Friedman, M., & Schwartz, A. J. (1963). A Monetary History of the United States: 1867–1960. Princeton, NJ: Princeton Univ Press.
  22. Galbraith, J. W., & Tkacz, G. (2018). Nowcasting with payments system data. International Journal of Forecasting, 34(2), 366-376
  23. Hemmatian, F., & Sohrabi, M.(2019).A survey on classification techniques for opinion mining and sentiment analysis. Artificial intelligence review, 52(3), 1495-1545.
  24. Hu, Y., & Yao, J. (2022). Illuminating economic growth. Journal of Applied Econometrics, 37(5), 896-919.
  25. Kalamara, E., Turrell, A., Redl, C., Kapetanios, G., & Kapadia, S. (2022). Making text count: economic forecasting using newspaper text. Journal of Applied Econometrics, 37(5), 896-919.
  26. Keeney, M., Kennedy, B., & Liebermann, J. (2012). The value of hard and soft data for short-term forecasting of GDP. Economic Letters Series, 11/EL/12, Central Bank of Ireland.
  27. Keramatfar, A. (2021). Multi-stream modeling of comments’ contexts for sentiment analysis. Ph.D. Thesis, University of Qom (In Persian).
  28. Lourenço, N., & Rua, A. (2021). The Daily Economic Indicator: tracking economic activity daily during the lockdown. Economic Modelling,100, 105500.
  29. Manchado Marcos, L. (2023). Nowcasting with Alternative Data (Bachelor's thesis, Universitat Politècnica de Catalunya).‏
  30. 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.
  31. Noferesti, M. (2021). Applied Econometric Time Series. Shahid Beheshti University Press, Tehran (In Persian).
  32. Park, H., & Konishi, S. (2016). Robust logistic regression modelling via the elastic net-type regularization and tuning parameter selection. Journal of Statistical Computation and Simulation,86(7), 1450-1461.
  33. Rajabi, Z., Valavi, M., & Hourali, M. (2022). Sentiment analysis methods in Persian text: A survey. Signal and Data Processing, 19(2), 107-132 (In Persian).
  34. Reisenbichler, M., & Reutterer, T. (2019). Topic modeling in marketing: recent advances and research opportunities. Journal of Business Economics, 89(3), 327-356.
  35. Richardson, A., van Florenstein Mulder, T., & Vehbi, T. (2021). Nowcasting GDP using machine-learning algorithms: A real-time assessment. International Journal of Forecasting,37(2), 941-948.
  36. Rothman, T., & Yakar, C. (2019). Empirical Analysis Тowards the Effect of Social Media on Cryptocurrency Price and Volume. European Scientific Journal, ESJ, 15, 31-52.
  37. Shapiro, A. H., Sudhof, M., & Wilson, D. J. (2022). Measuring news sentiment. Journal of econometrics, 228(2), 221-243.
  38. Shiller, R. J. (2020). Narrative economics: How stories go viral and drive major economic events. Princeton University Press.‏
  39. Souri, A. (2021). Advanced Econometrics: Volume Two. Noor Elm Press, Tehran (In Persian).
  40. Strycharz, J., Strauss, N., & Trilling, D. (2018). The role of media coverage in explaining stock market fluctuations: Insights for strategic financial communication. International Journal of Strategic Communication, 12(1), 67-85.
  41. Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., & Kappas, A. (2010). Sentiment strength detection in short informal text. Journal of the American society for information science and technology, 61(12), 2544-2558.
  42. 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.
  43. Valdez, D., Pickett, A. C., & Goodson, P. (2018). Topic modeling: latent semantic analysis for the social sciences. Social Science Quarterly, 99(5), 1665-1679.
  44. Wang, H., Wang, J., Zhang, Y., Wang, M., & Mao, C. (2019). Optimization of Topic Recognition Model for News Texts Based on LDA. Digit. Inf. Manag.,17(5), 257.
  45. Wilcox, R. R. (2019). Multicolinearity and ridge regression: results on type I errors, power and heteroscedasticity. Journal of applied statistics, 46(5), 946-957.
  46. Yoon, J. (2021). Forecasting of real GDP growth using machine learning models: Gradient boosting and random forest approach. Computational Economics, 57(1), 247-265
  47. Zarei, A., Feiz, D., & Taheri, Gh. (2021). Providing Social Market Intelligence Framework based on web 2.0 Using Text-Mining Technique on Social Media Websites (Case Study: Competitive Analysis between Samsung and Emersun Brands). Management Research in Iran, 24(4), 98-125 (In Persian)
Quarterly Journal of Applied Theories of Economics
Volume 11, Issue 3 - Serial Number 42
December 2024
Pages 135-164

Files

Share

How to cite

Statistics