IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2311.14419.html
   My bibliography  Save this paper

Narratives from GPT-derived Networks of News, and a link to Financial Markets Dislocations

Author

Listed:
  • Deborah Miori
  • Constantin Petrov

Abstract

Starting from a corpus of economic articles from The Wall Street Journal, we present a novel systematic way to analyse news content that evolves over time. We leverage on state-of-the-art natural language processing techniques (i.e. GPT3.5) to extract the most important entities of each article available, and aggregate co-occurrence of entities in a related graph at the weekly level. Network analysis techniques and fuzzy community detection are tested on the proposed set of graphs, and a framework is introduced that allows systematic but interpretable detection of topics and narratives. In parallel, we propose to consider the sentiment around main entities of an article as a more accurate proxy for the overall sentiment of such piece of text, and describe a case-study to motivate this choice. Finally, we design features that characterise the type and structure of news within each week, and map them to moments of financial markets dislocations. The latter are identified as dates with unusually high volatility across asset classes, and we find quantitative evidence that they relate to instances of high entropy in the high-dimensional space of interconnected news. This result further motivates the pursued efforts to provide a novel framework for the systematic analysis of narratives within news.

Suggested Citation

  • Deborah Miori & Constantin Petrov, 2023. "Narratives from GPT-derived Networks of News, and a link to Financial Markets Dislocations," Papers 2311.14419, arXiv.org.
  • Handle: RePEc:arx:papers:2311.14419
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2311.14419
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Fabrizio Lillo & Salvatore Miccich� & Michele Tumminello & Jyrki Piilo & Rosario N. Mantegna, 2015. "How news affects the trading behaviour of different categories of investors in a financial market," Quantitative Finance, Taylor & Francis Journals, vol. 15(2), pages 213-229, February.
    2. Paolo Pasquariello, 2014. "Financial Market Dislocations," The Review of Financial Studies, Society for Financial Studies, vol. 27(6), pages 1868-1914.
    3. Xinli Yu & Zheng Chen & Yuan Ling & Shujing Dong & Zongyi Liu & Yanbin Lu, 2023. "Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting," Papers 2306.11025, arXiv.org.
    4. So, Eric C. & Wang, Sean, 2014. "News-driven return reversals: Liquidity provision ahead of earnings announcements," Journal of Financial Economics, Elsevier, vol. 114(1), pages 20-35.
    5. Rick Steinert & Saskia Altmann, 2023. "Linking microblogging sentiments to stock price movement: An application of GPT-4," Papers 2308.16771, arXiv.org.
    6. Udit Gupta, 2023. "GPT-InvestAR: Enhancing Stock Investment Strategies through Annual Report Analysis with Large Language Models," Papers 2309.03079, arXiv.org.
    Full references (including those not matched with items on IDEAS)

    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. Han, Rui-Qi & Li, Ming-Xia & Chen, Wei & Zhou, Wei-Xing & Stanley, H. Eugene, 2019. "Structural properties of statistically validated empirical information networks," Physica A: Statistical Mechanics and its Applications, Elsevier, vol. 523(C), pages 747-756.
    2. Mahsa Samsami & Ralf Wagner, 2021. "Investment Decisions with Endogeneity: A Dirichlet Tree Analysis," JRFM, MDPI, vol. 14(7), pages 1-19, July.
    3. Takumi Sueshige & Didier Sornette & Hideki Takayasu & Misako Takayasu, 2019. "Classification of position management strategies at the order-book level and their influences on future market-price formation," PLOS ONE, Public Library of Science, vol. 14(8), pages 1-19, August.
    4. Hu, Yuan & Lindquist, W. Brent & Rachev, Svetlozar T. & Shirvani, Abootaleb & Fabozzi, Frank J., 2022. "Market complete option valuation using a Jarrow-Rudd pricing tree with skewness and kurtosis," Journal of Economic Dynamics and Control, Elsevier, vol. 137(C).
    5. Zhaobo Zhu & Licheng Sun & Chris Stivers, 2021. "Price anchors and short‐term reversals," Financial Management, Financial Management Association International, vol. 50(2), pages 425-454, June.
    6. Margarita Baltakienė & Kęstutis Baltakys & Juho Kanniainen & Dino Pedreschi & Fabrizio Lillo, 2019. "Clusters of investors around initial public offering," Palgrave Communications, Palgrave Macmillan, vol. 5(1), pages 1-14, December.
    7. T. T. Chen & B. Zheng & Y. Li & X. F. Jiang, 2017. "New approaches in agent-based modeling of complex financial systems," Papers 1703.06840, arXiv.org.
    8. Aytekin Ertan & Stephen A. Karolyi & Peter W. Kelly & Robert Stoumbos, 2022. "Earnings announcement return extrapolation," Review of Accounting Studies, Springer, vol. 27(1), pages 185-230, March.
    9. Chuang, Hongwei, 2016. "Brokers’ financial network and stock return," The North American Journal of Economics and Finance, Elsevier, vol. 36(C), pages 172-183.
    10. Sindhuja Ranganathan & Mikko Kivelä & Juho Kanniainen, 2018. "Dynamics of investor spanning trees around dot-com bubble," PLOS ONE, Public Library of Science, vol. 13(6), pages 1-14, June.
    11. Liu, Bibo & Wang, Huijun & Yu, Jianfeng & Zhao, Shen, 2020. "Time-varying demand for lottery: Speculation ahead of earnings announcements," Journal of Financial Economics, Elsevier, vol. 138(3), pages 789-817.
    12. van Binsbergen, Jules H. & Diamond, William F. & Grotteria, Marco, 2022. "Risk-free interest rates," Journal of Financial Economics, Elsevier, vol. 143(1), pages 1-29.
    13. repec:osf:socarx:mfx6w_v1 is not listed on IDEAS
    14. Liu, Junhao & Hope, Ole-Kristian & Hu, Danqi, 2023. "Earnings announcements in China: Overnight-intraday disparity," Journal of Corporate Finance, Elsevier, vol. 82(C).
    15. Vítor Manuel de Sousa-Gabriel & María Belén Lozano-García & Maria Fernanda Ludovina Inácio Matias & Maria Elisabete Neves & Jennifer Martínez-Ferrero, 2024. "Global environmental equities and investor sentiment: the role of social media and Covid-19 pandemic crisis," Review of Managerial Science, Springer, vol. 18(1), pages 105-129, January.
    16. Benson, Karen & Faff, Robert & Smith, Tom, 2015. "Injecting liquidity into liquidity research," Pacific-Basin Finance Journal, Elsevier, vol. 35(PB), pages 533-540.
    17. Huang, Wenqian & Ranaldo, Angelo & Schrimpf, Andreas & Somogyi, Fabricius, 2022. "Constrained Dealers and Market Efficiency," VfS Annual Conference 2022 (Basel): Big Data in Economics 264054, Verein für Socialpolitik / German Economic Association.
    18. Gianna Figà-Talamanca & Marco Patacca, 2024. "An explorative analysis of sentiment impact on S&P 500 components returns, volatility and downside risk," Annals of Operations Research, Springer, vol. 342(3), pages 2095-2117, November.
    19. Thierry Foucault & Roman Kozhan & Wing Wah Tham, 2017. "Toxic Arbitrage," The Review of Financial Studies, Society for Financial Studies, vol. 30(4), pages 1053-1094.
    20. Raeid Saqur, 2024. "What Teaches Robots to Walk, Teaches Them to Trade too -- Regime Adaptive Execution using Informed Data and LLMs," Papers 2406.15508, arXiv.org.
    21. Nina Karnaukh & Angelo Ranaldo & Paul Söderlind, 2015. "Understanding FX Liquidity," The Review of Financial Studies, Society for Financial Studies, vol. 28(11), pages 3073-3108.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    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:arx:papers:2311.14419. 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: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    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.