Vol. 39 No. 2 (2024): 78-vol. 39, no. 2, july-december, 2024
Articles

Regional sentiment indexes and their association with timely indicators of economic activity in Mexico, 2016-2021

pdf

PDF (Español)
pdf

XML
  • Leonardo E. Torre,
  • Eva E. González,
  • Luis R. Casillas,
  • Jorge A. Alvarado
Leonardo E. Torre
Banco de México
Eva E. González
Banco de México
Luis R. Casillas
Banco de México
Jorge A. Alvarado
Banco de México
DOI: https://doi.org/10.24201/ee.v39i2.455

Published 2024-07-31

Keywords

  • sentiment analysis,
  • machine learning,
  • regional analysis,
  • Mexico

How to Cite

Torre, L. E., González, E. E., Casillas, L. R., & Alvarado, J. A. (2024). Regional sentiment indexes and their association with timely indicators of economic activity in Mexico, 2016-2021. Estudios Económicos De El Colegio De México, 39(2), 349–419. https://doi.org/10.24201/ee.v39i2.455

Metrics

Abstract

We estimate sentiment indexes at the regional and national level using text data obtained from the Programa Trimestral de Entrevistas a Directivos del Banco de México, used to elaborate the Report on the Regional Economies regarding the factors that the interviewed consider affected, affect, or could affect economic activity in their sector or state. Using text data from quarterly interviews performed from January 2016 to January 2021, we associate these indexes with different indicators of regional and national economic activity published by INEGI. The estimates indicate positive and statistically significant correlations among the sentiment indexes and some economic activity indicators. Since the sentiment indexes can be estimated relatively faster than most of the traditional economic indicators analyzed, this paper outlines the relevance of the text data contained in the Programa Trimestral de Entrevistas a Directivos to supplement the information obtained from traditional indicators.

pdf

PDF (Español)
pdf

XML

Downloads

Download data is not yet available.

References

  1. Algaba, A., D. Gardia, K. Bluteau, S. Borms y K. Boudt. 2020. Econometrics meets sentiment: An overview of methodology and applications, Journal of Economic Surveys, 34(3): 512-547. DOI: https://doi.org/10.1111/joes.12370
  2. Alloghani, M., D. Al-Jumeily, J. Mustafina, A. Hussain y A.J. Aljaaf. 2020. A systematic review on supervised and unsupervised machine learning algorithms for data science, en M. Berry, A. Mohamed y B. Yap (eds.), Supervised and Unsupervised Learning for Data Science, Springer. DOI: https://doi.org/10.1007/978-3-030-22475-2_1
  3. Anandarajan, M., C. Hill y T. Nolan. 2019. Semantic space representation and latent semantic analysis, en Practical Text Analytics, Advances in Analytics and Data Science, Vol. 2, Springer. DOI: https://doi.org/10.1007/978-3-319-95663-3
  4. Aragón, M., M. Carmona, M. Montes, H. Escalante, L. Villaseñor y D. Moctezuma. 2019. Overview of MEX-A3T at IberLEF 2019: Authorship and aggressiveness analysis in Mexican Spanish tweets, documento presentado en SEPLN Workshop on Iberian Languages Evaluation Forum (IberLEF), Bilbao.
  5. Arora, S. 2021. Data mining vs. machine learning: The key difference, www.simplilearn.com/data-mining-vs-machine-learning-article.
  6. Athey, S. 2018. The impact of machine learning on Economics, en A. Agrawal, J. Gans y A. Goldfarb (eds.), The Economics of Artificial Intelligence: An Agenda, National Bureau of Economic Research.
  7. Azqueta-Gavaldón, A., D. Hirschbühl, L. Onorante y L. Saiz. 2020. Economic policy uncertainty in the Euro area: An unsupervised machine learning approach, Working Paper Series No. 2359, European Central Bank. DOI: https://doi.org/10.2139/ssrn.3516756
  8. Banco de México. 2015. Informe trimestral octubre-diciembre, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7B94CE88E5-3F13-4707-8038-30A0F49D6E47%7D.pdf.
  9. Banco de México. 2016a. Informe trimestral enero-marzo, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7BA3AA2471-B70C-DAA2-01DF-EA06C6546B6A%7D.pdf
  10. Banco de México. 2016b. Informe trimestral abril-junio, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7BAD156BB0-60B7-947E-A9EF-9C96AB882667%7D.pdf.
  11. Banco de México. 2016c. Informe trimestral julio-septiembre, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7BD093DF85-0D83-3DD2-A533-3431AFAFE3A1%7D.pdf.
  12. Banco de México. 2019. Informe trimestral octubre-diciembre, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7B0DED33B2-FF70-345D-53BE-77EA35A0D743%7D.pdf.
  13. Banco de México. 2020a. Informe trimestral enero-marzo, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7B23C2DCA8-4AD3-FBE0-B0BF-4D30C8066B84%7D.pdf.
  14. Banco de México. 2020b. Reporte sobre las economías regionales julio-septiembre, https://www.banxico.org.mx/publicaciones-y-prensa/reportes-sobre-las-economias-regionales/%7B8427BCB2-D8F2-C28A-8DD4-EB8DD9770681%7D.pdf.
  15. Banco de México. 2020c. Informe trimestral octubre-diciembre, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7B81BD569D-DD6E-885A-A67F-5664A37B4148%7D.pdf.
  16. Banco de México. 2021. Informe trimestral enero-marzo, https://www.banxico.org.mx/publicaciones-y-prensa/informes-trimestrales/%7B49D9C039-CE93-FC5A-59A6-DFF7579FDB26%7D.pdf.
  17. Barocas, S. 2014. Data mining and the discourse on discrimination, documento presentado en KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, California.
  18. Benhabib, J. y M. Spiegel. 2017. Sentiment and economic activity: Evidence from U.S. states, NBER Working Paper No. 23899. DOI: https://doi.org/10.3386/w23899
  19. Blei, D. 2011. Introduction to probabilistic topic models, Communications of the ACM, 55(4): 77-84. DOI: https://doi.org/10.1145/2133806.2133826
  20. Bojanowski, P., E. Grave, A. Joulin y T. Mikolov. 2017. Enriching word vectors with subword information, Transactions of the Association for Computational Linguistics, 5: 135-146. DOI: https://doi.org/10.1162/tacl_a_00051
  21. Boyd, D. y K. Crawford. 2012. Critical questions for big data: Provocations for a cultural, technological, and scholarly phenomenon, Information, Communication and Society, 15(5): 662-679. DOI: https://doi.org/10.1080/1369118X.2012.678878
  22. Campos-Vázquez, R.M., B. López-Araiza y E. Sergio. 2020. Grandes datos, Google y desempleo, Estudios Económicos, 35(1): 125-151. DOI: https://doi.org/10.24201/ee.v35i1.399
  23. Cho, K., B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk y Y. Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation, ArXiv preprint, arXiv:1406.1078. DOI: https://doi.org/10.3115/v1/D14-1179
  24. D’Andrea, A., F. Ferri, P. Grifoni y T. Guzzo. 2015. Approaches, tools and applications for sentiment analysis implementation, International Journal of Computer Applications, 125(3): 26-33. DOI: https://doi.org/10.5120/ijca2015905866
  25. De Bondt, G. y S. Schiaffi. 2015. Confidence matters for current economic growth: Empirical evidence for the Euro-area and the United States, Social Science Quarterly, 96(4): 1027-1040. DOI: https://doi.org/10.1111/ssqu.12181
  26. Devlin, J., M. Chang, K. Lee y K. Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding, ArXiv preprint, arXiv: 1810.04805.
  27. Díaz, M. y J. Huerta. 2020. Co-movimiento entre los índices de confianza del consumidor de México y Estados Unidos 2001-2018, Economía, Sociedad y Territorio, 20(62): 123-150. DOI: https://doi.org/10.22136/est20201379
  28. Doerr, S., L. Gambacorta y J. Serena. 2021. Big data and machine learning in central banking, BIS Working Paper No. 930, Bank for International Settlements.
  29. Garrett, T., R. Hernández-Murillo y M. Owyang. 2004. Does consumer sentiment predict regional consumption?, Federal Reserve Bank of St. Louis Review, 87(2): 123-35. DOI: https://doi.org/10.20955/r.87.123-135
  30. Gentzkow, M., K. Bryan y M. Taddy. 2019. Text as data, Journal of Economic Literature, 57(3): 535-574. DOI: https://doi.org/10.1257/jel.20181020
  31. González, C. y M. Herman. 2020. Foreign exchange forecasting via machine learning, https://cs229.stanford.edu/proj2018/poster/76.pdf.
  32. Hatzivassiloglou, V. y K. McKeown. 2002. Predicting the semantic orientation of adjectives, en 35th Annual Meeting of the Association for Computational Linguistics, Madrid, Association for Computational Linguistics.
  33. Jurafsky, D. y J. Martin. 2020. Speech and language processing, tercera edición (borrador), https://web.stanford.edu/~jurafsky/slp3/.
  34. Kay, M, C. Matuszek y S. Munson. 2015. Unequal representation and gender stereotypes in image search results for occupations, en Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, Nueva York, Association for Computational Linguistics. DOI: https://doi.org/10.1145/2702123.2702520
  35. Kim, S. y E. Hovy. 2004. Determining the sentiment of opinions, en Proceedings of International Conference on Computational Linguistics, Ginebra, Coling. DOI: https://doi.org/10.3115/1220355.1220555
  36. Korab, P. 2021. Use of machine learning in economic research: What the literature tells us, https://towardsdatascience.com/use-of-machine-learning-in-economic-research.
  37. Medhat, W., A. Hassan y H. Korashy. 2014. Sentiment analysis algorithms and applications: A survey, Ain Shams Engineering Journal, 5(4): 1093-1113. DOI: https://doi.org/10.1016/j.asej.2014.04.011
  38. Miller, C. y C. Dwork. 2015. Algorithms and bias: Q. and A., New York Times,
  39. http://www.nytimes.com/2015/08/11/upshot/algorithms-and-bias-q-and-a-with-cynthia-dwork.html.
  40. Moritz, H. 2014. How big data is unfair, https://medium.com/@mrtz/how-big-data-is-unfair-9aa544d739de.
  41. Muñiz, V. 2020. Una consulta sobre técnicas de aprendizaje automático, Entrevista presencial, Centro de Investigación en Matemáticas A.C. Monterrey.
  42. Nasukawa, T. y J. Yi. 2003. Sentiment Analysis: Capturing Favorability using Natural Language Processing, Nueva York, Association for Computing Machinery. DOI: https://doi.org/10.1145/945645.945658
  43. Pang, B., L. Lee y S. Vaithyanathan. 2002. Thumbs up? Sentiment classification using machine learning techniques, en Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Nueva York, Association for Computational Linguistics.
  44. Pinto, S. 2019. Sentiment analysis of the fifth district manufacturing and service surveys, Economic Quarterly, 105(9): 133-164. DOI: https://doi.org/10.21144/eq1050301
  45. Prabowo, R. y M. Thelwall. 2009. Sentiment analysis: A combined approach, Journal of Informetrics, 3(2): 143-157. DOI: https://doi.org/10.1016/j.joi.2009.01.003
  46. Rho, C., R. Fernández y B. Palma. 2021. A sentiment based indicator for the Mexican financial sector, Documento de Investigación No. 2021-04, Banco de México. DOI: https://doi.org/10.36095/banxico/di.2021.04
  47. Rosenbaum, P. y D. Rubin. 1983. The central role of the propensity score in observational studies for causal effects, Biometrika, 70(1): 41-55. DOI: https://doi.org/10.1093/biomet/70.1.41
  48. Salhin, A., M. Sherif y E. Jones. 2016. Managerial sentiment, consumer confidence and sector returns, International Review of Financial Analysis, 47: 24-38. DOI: https://doi.org/10.1016/j.irfa.2016.06.009
  49. Santero, T. y N. Westerlund. 1996. Confidence indicators and their relationship with changes in economic activity, OECD Working Papers No. 170.
  50. Stsiopkina, M. 2022. Hard vs. soft data: The difference, https://oxylabs.io/blog/hard-data-vs-soft-data.
  51. Suss, J. y H. Treitel. 2019. Predicting bank distress in the UK with machine learning, Staff Working Paper No. 831, Bank of England. DOI: https://doi.org/10.2139/ssrn.3465753
  52. Sutton, R. y A. Barto. 2018. Reinforcement Learning, Estados Unidos, The MIT Press.
  53. Sweeney, L. 2013. Discrimination in on-line ad delivery, Queue, 11(3): 1-20. DOI: https://doi.org/10.1145/2460276.2460278
  54. Taboada, M., J. Brooke, T. Tofiloski, K. Voll y M. Stede. 2011. Lexicon-based methods for sentiment analysis, Computational Linguistics, 37(2): 267-307. DOI: https://doi.org/10.1162/COLI_a_00049
  55. Turney, P. 2002. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews, ArXiv preprint, arXiv:cs/0212032. DOI: https://doi.org/10.3115/1073083.1073153
  56. Uno, Y. y K. Adachi. 2019. Calculating non-response bias in firms’ inflation expectations using machine learning techniques, Working Paper Series No.19-E-17, Bank of Japan.
  57. Wallach, H. 2014. Big data, machine learning, and the social sciences: Fairness, accountability, and transparency, https://medium.com/@hannawallach/big-data-machine-learning-and-the-social-sciences-927a8e20460d.
  58. Weng, L. 2021. Learning with not enough data. Part 1: Semi-supervised learning, https://lilianweng.github.io/posts/2021-12-05-semi-supervised/
  59. Wiesalla, L. 2021. The machine learning workflow. Concepts and applications, https://www.nextlytics.com/blog/machine-learning-workflow.
  60. Witten, I., E. Frank, M. Hall y C. Pall. 2017. Data Mining: Practical Machine Learning Tools and Techniques, Elsevier, Morgan Kaufmann Publishers.