Affiliation:
1. National Bank of Ukraine
Abstract
This research highlights the role played by the media in the formation of inflation expectations among various respondents in Ukraine. Using a large news corpus and machine-learning techniques, I have constructed newsbased metrics that produce quantitative indicators for texts, which show if the news topics are relevant to inflation expectations. I have found evidence that various news topics may have an impact on inflation expectations, and can explain part of their variance. Thus, my results could help in the analysis of inflation expectations – which is of value, given that anchoring inflation expectations remains a key challenge for central banks.
Reference36 articles.
1. Angelico, C., Marcucci, J., Miccoli, M., Quarta, F. (2021). Can we measure inflation expectations using Twitter? Bank of Italy Working Papers, 1318. Rome: Bank of Italy. Retrieved from https://www.bancaditalia.it/pubblicazioni/temidiscussione/2021/2021-1318/en_tema_1318.pdf
2. Azqueta-Gavaldón, A. (2017). Developing news-based Economic Policy Uncertainty index with unsupervised machine learning. Economics Letters, 158, 47–50. https://doi.org/10.1016/j.econlet.2017.06.032
3. Baker, S. R., Bloom, N., Davis, S. J. (2016). Measuring economic policy uncertainty. The Quarterly Journal of Economics, 131(4), 1593–1636. https://doi.org/10.1093/qje/qjw024
4. Bauer, M. D. (2015). Inflation expectations and the news. International Journal of Central Banking, 11(2), 1-40. Retrieved from https://www.ijcb.org/journal/ijcb15q2a1.pdf
5. Blei, D. M., Ng, A. Y., Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3, 993–1022. Retrieved from https://dl.acm.org/doi/10.5555/944919.944937