Abstract
Inflationary forecasts tend to play a crucial role in macroeconomic and financial decision/policy making. In particular, in an inflation-targeting framework, it is of paramount importance. While traditionally, model-based and survey-based inflation expectations are being used, in recent times, a literature has emerged to forecast various macro-aggregates using text-based sentiment estimates. Taking a cue from this approach, in this paper we attempt to decipher inflationary sentiments using text mining from two leading financial dailies, viz., the Economic Times and Business Line. We consciously avoid using social media news due to severe challenges and high noise-to-signal ratio. In our algorithm we aggregate CPI basket level (viz., food, fuel, cloth & miscellaneous) sentiment into an overall index of inflation, adapting techniques from natural language processing. Our results from this text-based model indicate significant success in tracking actual inflation.
Similar content being viewed by others
Notes
See Dua (2020) for a detailed discussion on monetary policy framework in India.
Interestingly, an analysis of IESH in a recent RBI study revealed, “Ever since the inception of the survey, households’ inflation expectations are found to have an upward bias, when compared with the actual inflation, by about 300 basis points on an average for the three months ahead horizon and 400 basis points for the one year ahead horizon” (RBI, 2019). In fact, IESH does not appear to be efficient (Sharma and Bicchal, 2018).
We thank an anonymous reviewer and an Associate Editor for their many helpful comments.
Illustratively, RBI Executive Director (in charge of monetary policy) in a speech noted, “The RBI’s inflation expectations survey of households provides a measurement of the sentiment of inflation expectations that is essentially urban” (Mohanty, 2012).
We are indebted to an anonymous referee for pointing this explicitly to us.
We are indebted to an anonymous referee for pointing out this subtle difference.
Incidentally, the RBI also used this CPI-based inflation for its flexible inflation targeting policy.
As is well-known, Python is an interpreted, object-oriented, high-level programming language with dynamic semantics; see https://www.python.org/doc/essays/ for details.
A global news monitoring and search engine, owned by the Dow Jones & Company.
The relevant weights for each of these groups are 45.86%, 2.38%, 6.53%, 10.07%, 6.84%, and 28.32%, respectively.
NLTK stands for Natural Language Toolkit. This toolkit is an NLP library which contains packages to make machines understand human language and reply to it with an appropriate response.
An encouraging development is a recent RBI article which found that the sentiment index (derived through text) has significant predictive ability for retail inflation in India; see RBI (2020).
References
Bernanke, BS (2007) Inflation Expectations and Inflation Forecasting, Speech at the Monetary Economics Workshop of the NBER, July 10. https://www.federalreserve.gov/newsevents/speech/bernanke20070710a.htm
Bholat, D., Hansen, S., Santos, P., & Schonhardt-Bailey, C. (2015). Text Mining for Central Banks (p. 33). CCBS Handbook No: Bank of England.
Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1–8.
Brandt, M. W., & Gao, L. (2019). Macro fundamentals or geopolitical events? A textual analysis of news events for crude oil. Journal of Empirical Finance, 51, 64–94.
Bullard, J (2016) Inflation Expectations Are Important to Central Bankers, Too”, Fed St Louis Regional Economist, April, https://www.stlouisfed.org/publications/regional-economist/april-2016/inflation-expectations-are-important-to-central-bankers-too
DeLong, B. J. (2002). Macroeconomics. New York: McGraw-Hill.
Dua, P. (2020). Monetary policy framework in India. Indian Economic Review, 55, 117–154.
Boschen J. and Mills, S. (1995). “The relation between narrative and money market indicators of monetary policy”, Economic inquiry, January, pp 24–44.
Romer, C. D. and Romer, D. H. (2004). "A New Measure of Monetary Shocks: Derivation and Implications", American Economic Review, September, 94(4): 1054 - 1083.
Friedman, M., & Schwartz, A. J. (1972). A Monetary History of the United States, 1867–1960. Princeton: Princeton University Press.
Gkotsis, G, Velupillai, S, Oellrich, A, Dean, H, Liakata, M, Dutta, R (2016).Don't Let Notes Be Misunderstood: A Negation Detection Method for Assessing Risk of Suicide in Mental Health Records. In Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology, pp 95–105
Government of India. (2017). Economic Survey, 2016–17. Delhi: Government of India.
Honnibal, M., and Johnson, M. (2015). An improved, non-monotonic system for dependency parsing. Empirical Methods in Natural Language Processing (EMNLP), pp 1373–1378.
Hu, M. and Liu, B. (2004). Mining and summarising customer reviews. Knowledge and Data Discovery (KDD), pp 168–177
Jin, W. and Ho, H.H. (2009). A novel lexicalised hmm-based learning framework for web opinion mining. In International Conference on Machine Learning (ICML), pp 465–472
Lakkaraju, H., Bhattacharya, C., Bhattacharya, I., and Merugu, S. (2011). Exploiting coherence in reviews for discovering latent facets and associated sentiments. Siam International Conference on Data Mining (SDM), pp 498–509
Levenberg, A., Pulman, S., Moilanen, K., Simpson, E., & Roberts, S. (2014). Predicting economic indicators from web text using sentiment composition. International Journal of Computer and Communication Engineering, 3(2), 109–115.
Liu, B. (2012). Sentiment Analysis and Opinion Mining, Morgan and Claypool Publishers
Looper, E and Bird, S. (2002). NLTK: The natural language toolkit. Effective Tools and Methodologies for Teaching Natural Language Processing, (ETMTNLP), pp 63–70.
McCallum, A. and Nigam, K. (1998). “A comparison of event models for naive bayes text classification. In Association for the Advancement of Artificial Intelligence (AAAI), pp 41–48.
Mohanty, D. (2012) The importance of inflation expectations, Speech by Executive Director of the Reserve Bank of India, at the S P Jain Institute of Management & Research, Mumbai, November 9 2012, available at https://www.bis.org/review/r121112c.pdf
Nyman, R., Gregory, D., Kapadia, S., Ormerod, P., Tuckett, D., and Smith, R. (2016). News and narratives in financial systems: Exploiting big data for systemic risk assessment, Bank of England Working Paper No. 704.
Popescu A.M., Etzioni, O. (2005). Extracting Product Features and Opinions from reviews, Empirical Methods in Natural Language Processing (EMNLP), pp 339–346
RBI. (2019). Households’ Inflation Expectations: A Reflection, (Article prepared by Purnima Shaw, A. R. Jayaraman and Tushar B. Das in the Division of Household Surveys, Department of Statistics and Information Management of the RBI), RBI Bulletin, December, pp. 59–69.
RBI (2020): Inflation Decoded Through Power of Words, RBI Bulletin, May, pp. 9–23.
Shapiro, A. H.., Sudhof, M., and Wilson, D. (2018). Measuring News Sentiment. Federal Reserve Bank of San Francisco Working Paper, available at https://doi.org/https://doi.org/10.24148/wp2017-01
Sharma, N. K., & Bicchal, M. (2018). The properties of inflation expectations: Evidence for India. EconomiA, 19(1), 74–89.
Smith, N. (2018). Want a Recession Forecast: Ask a Machine, Bloomberg, May 13, 2018, available at https://www.bloomberg.com/view/articles/2018-05-11/want-a-recession-forecast-ask-a-machine-instead-of-an-economist
Funding
We acknowledge the data support provided by the Financial Research and Trading Laboratory of IIM Calcutta and research grant by IIM Calcutta.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Banerjee, A., Kanodia, A. & Ray, P. Deciphering Indian inflationary expectations through text mining: an exploratory approach. Ind. Econ. Rev. 56, 49–66 (2021). https://doi.org/10.1007/s41775-021-00106-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41775-021-00106-9