IDEAS home Printed from https://ideas.repec.org/a/bkr/journl/v81y2022i4p86-112.html
   My bibliography  Save this article

Macroeconomic Forecasting Using Data from Social Media

Author

Listed:
  • Elena Shulyak

    (HSE University)

Abstract

In this paper, I build a series of economic sentiment indices for Russia based on news posts and comments on them from the Russian social network VKontakte. Text from the social network is processed, and the Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture (GSDMM) model is used to highlight news posts on economic topics. To check whether the obtained indices really describe consumer and business sentiment, I compare them with existing indices: the Levada Center's consumer sentiment index and the Purchasing Managers' Index (PMI) for the manufacturing and service sectors in Russia. I use the indices constructed to predict macroeconomic indicators for Russia using machine learning methods (Random Forest, Extremely Randomised Trees, Gradient Boosting, and XGBoost). I compare the mean square errors (MSE) of the machine learning models with the MSEs of a first-order autoregressive model. In almost all cases, the errors of the machine learning models are smaller.

Suggested Citation

  • Elena Shulyak, 2022. "Macroeconomic Forecasting Using Data from Social Media," Russian Journal of Money and Finance, Bank of Russia, vol. 81(4), pages 86-112, December.
    • Handle: RePEc:bkr:journl:v:81:y:2022:i:4:p:86-112
    as

    Download full text from publisher

    File URL: https://rjmf.econs.online/upload/iblock/7db/Macroeconomic-Forecasting-Using-Data-from-Social-Media.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Jason Bram & Sydney C. Ludvigson, 1998. "Does consumer confidence forecast household expenditure? a sentiment index horse race," Economic Policy Review, Federal Reserve Bank of New York, vol. 4(Jun), pages 59-78.
    2. Scott R. Baker & Nicholas Bloom & Steven J. Davis, 2016. "Measuring Economic Policy Uncertainty," The Quarterly Journal of Economics, President and Fellows of Harvard College, vol. 131(4), pages 1593-1636.
    3. Andres Algaba & David Ardia & Keven Bluteau & Samuel Borms & Kris Boudt, 2020. "Econometrics Meets Sentiment: An Overview Of Methodology And Applications," Journal of Economic Surveys, Wiley Blackwell, vol. 34(3), pages 512-547, July.
    4. Ardia, David & Bluteau, Keven & Boudt, Kris, 2019. "Questioning the news about economic growth: Sparse forecasting using thousands of news-based sentiment values," International Journal of Forecasting, Elsevier, vol. 35(4), pages 1370-1386.
    5. Larsen, Vegard H. & Thorsrud, Leif A., 2019. "The value of news for economic developments," Journal of Econometrics, Elsevier, vol. 210(1), pages 203-218.
    6. Gabe J. Bondt & Stefano Schiaffi, 2015. "Confidence Matters for Current Economic Growth: Empirical Evidence for the Euro Area and the United States," Social Science Quarterly, Southwestern Social Science Association, vol. 96(4), pages 1027-1040, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Urmat Dzhunkeev, 2024. "Forecasting Inflation in Russia Using Gradient Boosting and Neural Networks," Russian Journal of Money and Finance, Bank of Russia, vol. 83(1), pages 53-76, March.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Stolbov, Mikhail & Shchepeleva, Maria & Karminsky, Alexander, 2022. "When central bank research meets Google search: A sentiment index of global financial stress," Journal of International Financial Markets, Institutions and Money, Elsevier, vol. 81(C).
    2. Julian Ashwin & Eleni Kalamara & Lorena Saiz, 2024. "Nowcasting Euro area GDP with news sentiment: A tale of two crises," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 39(5), pages 887-905, August.
    3. Luca Barbaglia & Sergio Consoli & Sebastiano Manzan, 2024. "Forecasting GDP in Europe with textual data," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 39(2), pages 338-355, March.
    4. Jon Ellingsen & Vegard H. Larsen & Leif Anders Thorsrud, 2020. "News media vs. FRED-MD for macroeconomic forecasting," Working Papers No 08/2020, Centre for Applied Macro- and Petroleum economics (CAMP), BI Norwegian Business School.
    5. Andres Algaba & David Ardia & Keven Bluteau & Samuel Borms & Kris Boudt, 2020. "Econometrics Meets Sentiment: An Overview Of Methodology And Applications," Journal of Economic Surveys, Wiley Blackwell, vol. 34(3), pages 512-547, July.
    6. Jon Ellingsen & Vegard H. Larsen & Leif Anders Thorsrud, 2022. "News media versus FRED‐MD for macroeconomic forecasting," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 37(1), pages 63-81, January.
    7. Gerardin Mathilde, & Ranvier Martial., 2021. "Enrichment of the Banque de France’s monthly business survey: lessons from textual analysis of business leaders’ comments," Working papers 821, Banque de France.
    8. David Ardia & Keven Bluteau, 2024. "Optimal Text-Based Time-Series Indices," Papers 2405.10449, arXiv.org.
    9. Nyman, Rickard & Kapadia, Sujit & Tuckett, David, 2021. "News and narratives in financial systems: Exploiting big data for systemic risk assessment," Journal of Economic Dynamics and Control, Elsevier, vol. 127(C).
    10. Hubert, Paul & Labondance, Fabien, 2021. "The signaling effects of central bank tone," European Economic Review, Elsevier, vol. 133(C).
    11. Saiz, Lorena & Ashwin, Julian & Kalamara, Eleni, 2021. "Nowcasting euro area GDP with news sentiment: a tale of two crises," Working Paper Series 2616, European Central Bank.
    12. Eleni Kalamara & Arthur Turrell & Chris Redl & George Kapetanios & Sujit Kapadia, 2022. "Making text count: Economic forecasting using newspaper text," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 37(5), pages 896-919, August.
    13. Aromi, J. Daniel & Clements, Adam, 2021. "Facial expressions and the business cycle," Economic Modelling, Elsevier, vol. 102(C).
    14. Simionescu, Mihaela, 2022. "Econometrics of sentiments- sentometrics and machine learning: The improvement of inflation predictions in Romania using sentiment analysis," Technological Forecasting and Social Change, Elsevier, vol. 182(C).
    15. Marc Burri & Daniel Kaufmann, 2020. "A daily fever curve for the Swiss economy," Swiss Journal of Economics and Statistics, Springer;Swiss Society of Economics and Statistics, vol. 156(1), pages 1-11, December.
    16. Jean-Charles Bricongne & Baptiste Meunier & Raquel Caldeira, 2024. "Should Central Banks Care About Text Mining? A Literature Review," Working papers 950, Banque de France.
    17. Lin, Jianhao & Mei, Ziwei & Chen, Liangyuan & Zhu, Chuanqi, 2023. "Is the People's Bank of China consistent in words and deeds?," China Economic Review, Elsevier, vol. 78(C).
    18. repec:hal:spmain:info:hdl:2441/3mgbd73vkp9f9oje7utooe7vpg is not listed on IDEAS
    19. Dorinth van Dijk & Jasper de Winter, 2023. "Nowcasting GDP using tone-adjusted time varying news topics: Evidence from the financial press," Working Papers 766, DNB.
    20. Laura Battaglia & Timothy Christensen & Stephen Hansen & Szymon Sacher, 2024. "Inference for Regression with Variables Generated from Unstructured Data," CESifo Working Paper Series 11119, CESifo.
    21. Paul Hubert & Fabien Labondance, 2019. "Central bank tone and the dispersion of views within monetary policy committees," SciencePo Working papers Main hal-03403256, HAL.

    More about this item

    Keywords

    machine learning; text analysis; gradient boosting; data analysis; text clustering;
    All these keywords.

    JEL classification:

    • C38 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Classification Methdos; Cluster Analysis; Principal Components; Factor Analysis
    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods
    • C55 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Large Data Sets: Modeling and Analysis

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:bkr:journl:v:81:y:2022:i:4:p:86-112. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Olga Kuvshinova (email available below). General contact details of provider: https://edirc.repec.org/data/cbrgvru.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.