Sosyal Medyada Ekonomik Belirsizlik: X Gönderilerinin Ekonomik ve Finansal Göstergeler Üzerindeki Etkisi

Abstract

Bu çalışma, X (eski adıyla Twitter) sosyal medya platformunda ekonomik belirsizliğe dair paylaşımların, GSYİH, ticari banka kredileri ve New York Borsası (NYSE) gibi ekonomik ve finansal göstergeler üzerindeki etkisini incelemektedir. Analiz, ABD’ye odaklanmıştır çünkü ülke, küresel finansal piyasalardaki lider konumu ve İngilizce X kullanıcılarının %50’sini oluşturan geniş kullanıcı kitlesiyle, sosyal medya kaynaklı ekonomik duyarlılık çalışmalar için ideal bir örnek teşkil etmektedir. Çalışmada, USA Gross Domestic Product Index, Commercial Bank Loans, New York Stock Exchange Composite ve X tabanlı Ekonomik Belirsizlik Endeksi (TEU) değişkenleri, Haziran 2011 - Nisan 2023 dönemine ait aylık verilerle analiz edilmiştir. Vektör Otoregresif (VAR) model yapılan araştırmada, ticari banka kredileri ve NYSE’deki değişimlerin GSYİH’yi önemli ölçüde etkilediği, TEU ile ölçülen ekonomik belirsizlik paylaşımlarının ise esasen banka kredilerindeki dalgalanmalara tepki verdiği bulunmuştur. Bulgular, GSYİH ile ticari banka kredileri arasında çift yönlü bir ilişki olduğunu göstermektedir; krediler, tüketici harcamaları ve yatırımlar yoluyla büyümeyi teşvik edebilirken, aşırı borçlanma istikrarsızlık ve krizlere yol açabilir. Ayrıca, TEU’nun yalnızca banka kredilerindeki değişimlerden etkilenmesi, sosyal medya duyarlılığının ABD ekonomisindeki kredi dinamiklerine özel bir hassasiyet gösterdiğini ortaya koymaktadır.

Keywords

• Ekonomik Belirsizlik
• Sosyal Medya
• GSYİH
• VAR

Economic Uncertainty on Social Media: The Impact of X Posts on Economic and Financial Indicators

Abstract

This study explores the influence of posts on the social media platform X (formerly Twitter) concerning economic uncertainty on key economic and financial indicators, including GDP, commercial bank loans, and the New York Stock Exchange (NYSE). The analysis focuses on the United States due to its pivotal role in global financial markets and the significant presence of U.S. users, who account for 50% of English-speaking X users, offering a rich dataset for studying social media-driven economic sentiment. Variables such as the USA Gross Domestic Product Index, Commercial Bank Loans, New York Stock Exchange Composite, and X-based Economic Uncertainty Index (TEU) were analyzed using monthly data from June 2011 to April 2023. Employing a Vector Autoregressive (VAR) model, the study finds that fluctuations in commercial bank loans and the NYSE Composite significantly impact GDP, while posts reflecting economic uncertainty, as captured by the TEU, primarily respond to changes in bank loans. The results reveal a bidirectional relationship between GDP and commercial bank loans, where loans can drive economic growth through increased consumer spending and investment, though excessive borrowing may lead to instability and crises. Furthermore, the TEU is influenced solely by variations in commercial bank loans, highlighting social media sentiment’s sensitivity to credit dynamics in the U.S. economy.

Keywords

• Economic Uncertainty
• Social Media
• GDP
• VAR

References

1. Ahmed, G., & Watters, C. (2018). A study of the relationship between the geographic locations of the user and participation in Twitter during different types of news events. Transactions on Machine Learning and Artificial Intelligence, 6(6). https://doi.org/10.14738/tmlai.66.5636
2. Alshammari, A., Kapetanakis, S., Evans, R., Polatidis, N., & Alshammari, G. (2019). User modeling on Twitter with exploiting explicit relationships for personalized recommendations. In Proceedings of the International Conference on Computational Intelligence and Data Science (pp. 135-145). https://doi.org/10.1007/978-3-030-14347-3_14
3. Alshammari, A., Kapetanakis, S., Polatidis, N., Evans, R., & Alshammari, G. (2019). Twitter user modeling based on indirect explicit relationships for personalized recommendations. In Proceedings of the International Conference on Computational Intelligence and Data Science (pp. 93-105). https://doi.org/10.1007/978-3-030-28377-3_8
4. Ashraf, B. (2021). Is economic uncertainty a risk factor in bank loan pricing decisions? International evidence. Risks, 9(5), 81. https://doi.org/10.3390/risks9050081
5. Baker, S. R., Bloom, N., Davis, S., & Renault, T. (2021). Twitter-derived measures of economic uncertainty: Technical report.
6. Bai, P., Bai, Y., Safikhani, A., & Michailidis, G. (2021). Multiple change point detection in structured var models: the vardetect r package. arXiv preprint arXiv:2105.11007, https://doi.org/10.48550/arxiv.2105.11007
7. Bashir, F., & Wei, H. (2018). Handling missing data in multivariate time series using a vector autoregressive model-imputation (VAR-IM) algorithm. Neurocomputing, 276, 23-30. https://doi.org/10.1016/j.neucom.2017.03.097
8. Bertapelle, J., & Ballard-Reisch, D. (2015). Cultivating connections in 140 characters: A case study of Twitter relationship building. Media Watch, 6(3), 273. https://doi.org/10.15655/mw/2015/v6i3/77888

9. Bongomin, G., Ntayi, J., Munene, J., & Malinga, C. (2017). The relationship between access to finance and growth of SMEs in developing economies. Review of International Business and Strategy, 27(4), 520-538. https://doi.org/10.1108/ribs-04-2017-0037
10. Bringmann, L., Ferrer, E., Hamaker, E., Borsboom, D., & Tuerlinckx, F. (2018). Modeling nonstationary emotion dynamics in dyads using a time-varying vector-autoregressive model. Multivariate Behavioral Research, 53(3), 293-314. https://doi.org/10.1080/00273171.2018.1439722
11. Bordo, M., Duca, J., & Koch, C. (2016). Economic policy uncertainty and the credit channel: Aggregate and bank level U.S. evidence over several decades. WP, 2016(1605). https://doi.org/10.24149/wp1605
12. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1-8. https://doi.org/10.1016/j.jocs.2010.12.007
13. Bulteel, K., Mestdagh, M., Tuerlinckx, F., & Ceulemans, E. (2018). VAR(1) based models do not always outpredict AR(1) models in typical psychological applications. Psychological Methods, 23(4), 740-756. https://doi.org/10.1037/met0000178
14. Bulteel, K., Tuerlinckx, F., Brose, A., & Ceulemans, E. (2016). Clustering vector autoregressive models: Capturing qualitative differences in within-person dynamics. Frontiers in Psychology, 7. https://doi.org/10.3389/fpsyg.2016.01540
15. Choi, M., Sang, Y., & Park, H. (2014). Exploring political discussions by Korean Twitter users. Aslib Journal of Information Management, 66(6), 582-602. https://doi.org/10.1108/ajim-11-2012-0089
16. Dablander, F., Ryan, O., & Haslbeck, J. (2020). Choosing between AR(1) and VAR(1) models in typical psychological applications. PLOS ONE, 15(10), e0240730. https://doi.org/10.1371/journal.pone.0240730
17. Deng, W., & Yang, Y. (2021). Cross-platform comparative study of public concern on social media during the COVID-19 pandemic: An empirical study based on Twitter and Weibo. International Journal of Environmental Research and Public Health, 18(12), 6487. https://doi.org/10.3390/ijerph18126487
18. Durani, F. (2024). Time-varying relationship between fossil fuel-free energy indices and economic uncertainty: Global evidence from wavelet coherence approach. International Journal of Energy Economics and Policy, 14(1), 663-672. https://doi.org/10.32479/ijeep.15257
19. Ghosh, A. (2016). Do real estate loans reflect regional banking and economic conditions? Journal of Financial Economic Policy, 8(1), 37-63. https://doi.org/10.1108/jfep-09-2015-0050
20. Gilbert, E., & Karahalios, K. (2010). Widespread worry and the stock market. Proceedings of the International AAAI Conference on Web and Social Media, 4(1), 58-65.
21. Gunarto, T., Ciptawaty, U., Russel, E., & Yuliawan, D. (2023). How is the modeling of the relationship between food ınflation and the agricultural sector composite stock price ındex with the statistical analysis system?. In International Conference of Economics, Business, and Entrepreneur (ICEBE 2022) (pp. 535-544). Atlantis Press. https://doi.org/10.2991/978-2-38476-064-0_54
22. Granger, C. W. J. (1969). Investigating Causal Relations by Econometric Models and CrossSpectral Methods, Econometrica, 37, 424-438.
23. Grover, P., & Kar, A. (2020). Mining the social discussions surrounding circular economy: Insights from the collective intelligence shared in Twitter. In Proceedings of the International Conference on Computational Intelligence and Data Science (pp. 303-314). https://doi.org/10.1007/978-3-030-64861-9_27
24. Haslbeck, J., Bringmann, L., & Waldorp, L. (2020). A tutorial on estimating time-varying vector autoregressive models. Multivariate Behavioral Research, 56(1), 120-149. https://doi.org/10.1080/00273171.2020.1743630
25. Hendry, D. F., & Juselius, K. (2001). Explaining cointegration analysis: Part II. The Energy Journal, 22(1), 75-120.
26. Hughes, D., Rowe, M., Batey, M., & Lee, A. (2012). A tale of two sites: Twitter vs. Facebook and the personality predictors of social media usage. Computers in Human Behavior, 28(2), 561-569. https://doi.org/10.1016/j.chb.2011.11.001
27. Ibrahim, A., Kashef, R., Li, M., Valencia, E., & Huang, E. (2020). Bitcoin network mechanics: Forecasting the BTC closing price using vector auto-regression models based on endogenous and exogenous feature variables. Journal of Risk and Financial Management, 13(9), 189. https://doi.org/10.3390/jrfm13090189
28. Kılınç, G., Kocabiyik, T., & Karaatli, M. (2023). Baltic dry index estimation with NARX neural network model. Ekonomika, 102(1), 60-80. https://doi.org/10.15388/ekon.2023.102.1.4
29. Kim, W., & Chae, B. (2018). Understanding the relationship among resources, social media use and hotel performance. International Journal of Contemporary Hospitality Management, 30(9), 2888-2907. https://doi.org/10.1108/ijchm-02-2017-0085
30. Kwak, H., Lee, C., Park, H., & Moon, S. (2010). What is Twitter, a social network or a news media? https://doi.org/10.1145/1772690.1772751
31. Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Evidence from accounting reports. The Journal of Finance, 66(1), 35-65.
32. Lu, M. (2001). Vector autoregression (VAR) — An approach to dynamic analysis of geographic processes. Geografiska Annaler Series B Human Geography, 83(2), 67-78. https://doi.org/10.1111/j.0435-3684.2001.00095.x
33. Lynn, T., Rosati, P., Nair, B., & Bhaird, C. (2020). An exploratory data analysis of the #crowdfunding network on Twitter. Journal of Open Innovation Technology Market and Complexity, 6(3), 80. https://doi.org/10.3390/joitmc6030080
34. Monchen, G., Sinquin, B., & Verhaegen, M. (2019). Recursive Kronecker-based vector autoregressive identification for large-scale adaptive optics. IEEE Transactions on Control Systems Technology, 27(4), 1677-1684. https://doi.org/10.1109/tcst.2018.2834521
35. Morina, F., & Özen, E. (2020). Does the commercial bank's loans affect economic growth? Empirical evidence for the real sector economy in Kosovo (2005-2018). International Journal of Sustainable Development and Planning, 15(8), 1205-1222. https://doi.org/10.18280/ijsdp.150807
36. Nazir, N., Bashir, Z., Izhar, S., & Jamshed, Y. (2023). Sources of uncertainty and their impact on stock prices evidence from emerging economies. Financial Internet Quarterly, 19(2), 49-67. https://doi.org/10.2478/fiqf-2023-0012
37. Pripoaie, R., Crețu, C., Turtureanu, A., Sîrbu, C., Marinescu, E., Talaghir, L., … & Robu, D. (2022). A statistical analysis of the migration process: A case study—Romania. Sustainability, 14(5), 2784. https://doi.org/10.3390/su14052784
38. Ranco, G., Aleksovski, D., Caldarelli, G., & Grčar, M. (2015). The effects of Twitter sentiment on stock price returns. PloS one, 10(9), e0138441.
39. Raunig, B., Scharler, J., & Sindermann, F. (2016). Do banks lend less in uncertain times? Economica, 84(336), 682-711. https://doi.org/10.1111/ecca.12211
40. Ruan, Y., Alfantoukh, L., & Durresi, A. (2015). Exploring stock market using Twitter trust network. https://doi.org/10.1109/aina.2015.217
41. Rusman Al, I.; Ruchjana, B. N. Sukono,(2019) Vector autoregressive (VAR) model for rain-fall forecasting in west java indonesia at the peak of the rainy season. International Journal of Recent Technology and Engineering, 8.2: 216-223.https://doi.org/10.35940/ijrte.b1054.0782s719
42. Sarıkovanlık, V., Koy, A., Akkaya, M., Yıldırım, H. H., & Kantar, L. (2019). Finans biliminde ekonometri uygulamaları. Ankara: Seçkin Yayıncılık.
43. Shultz, L. (2023). Taming global citizenship education within Twitter’s attention economy. Journal of Creative Communications, 19(1), 13-31. https://doi.org/10.1177/09732586231198960
44. Souza, J., Reisen, V., Franco, G., Ispány, M., Bondon, P., & Santos, J. (2017). Generalized additive models with principal component analysis: An application to time series of respiratory disease and air pollution data. Journal of the Royal Statistical Society Series C (Applied Statistics), 67(2), 453-480. https://doi.org/10.1111/rssc.12239
45. Sprenger, T. O., Tumasjan, A., Sandner, P. G., & Welpe, I. M. (2014). Tweets and trades: The information content of stock microblogs. European Financial Management, 20(5), 926-957. https://doi.org/10.1111/j.1468-036X.2013.12007.x
46. Valencia, F. (2013). Aggregate uncertainty and the supply of credit. IMF Working Paper, 13(241), 1. https://doi.org/10.5089/9781475513936.001
47. Yang, J. H., Kong, Q. Z., Liu, H. J., & Peng, H. Y. (2021). Efficient Bayesian model class selection of vector autoregressive models for system identification. Structural Control and Health Monitoring, 28(9), e2780. https://doi.org/10.1002/stc.2780
48. Yeşiltaş, S., Arslan, B., & Altuğ, S. (2022). A Twitter-based economic policy uncertainty index: Expert opinion and financial market dynamics in an emerging market economy. Frontiers in Physics, 10, 864207. https://doi.org/10.3389/fphy.2022.864207
49. Wu, W., Tiwari, A., Gözgör, G., & Huang, L. (2021). Does economic policy uncertainty affect cryptocurrency markets? Evidence from Twitter-based uncertainty measures. Research in International Business and Finance, 58, 101478. https://doi.org/10.1016/j.ribaf.2021.101478
50. Zeitun, R., Rehman, M. U., Ahmad, N., & Vo, X. V. (2023). The impact of Twitter-based sentiment on US sectoral returns. The North American Journal of Economics and Finance, 64, 101847. https://doi.org/10.1016/j.najef.2023.101847
51. Yasin, H., Warsito, B., & Santoso, R. (2018). Soft computation vector autoregressive neural network (VAR-NN) GUI-based. E3S Web of Conferences, 73, 13008. https://doi.org/10.1051/e3sconf/20187313008