UNDERSTANDING MARKET NARRATIVES: AN INTERDISCIPLINARY APPROACH TO IDENTIFICATION AND ANALYSIS
DOI:
https://doi.org/10.46991/SBMP/2025.8.1.017Keywords:
Market narratives, Narrative economics, Behavioral finance, Investor sentiment, Natural language processing (NLP), Machine learning, Narrative identification, Sentiment analysisAbstract
Market narratives - collectively shared stories and economic discourses - significantly influence investor behavior, market sentiment, and asset pricing dynamics. The concept of narrative economics, pioneered by Robert Shiller, underscores the importance of understanding the propagation and impact of these narratives, particularly in today's digital era, where social media and digital news rapidly disseminate market stories. Despite the acknowledged importance, systematic identification and analysis of market narratives pose significant methodological challenges. Narratives are inherently subjective, dynamically evolving, and often embedded within large volumes of noisy textual data. This complexity complicates efforts to pinpoint narrative emergence, measure their influence on financial markets, and differentiate meaningful signals from market noise.
This article addresses the critical challenges associated with the scientific identification and analysis of market narratives. We explore interdisciplinary methodologies, integrating insights from behavioral finance, natural language processing (NLP), and machine learning to offer robust frameworks for narrative detection and assessment. The study critically reviews and evaluates methods including Structural Vector Autoregressions (SVARs) with narrative restrictions, redescription mining, storytelling algorithms, narrative mapping, news clustering, and textual analysis. Using empirical case studies, particularly focused on Microsoft Corporation, the effectiveness of each technique is analyzed, highlighting their respective strengths and limitations.
Our research proposes a hybrid analytical framework that combines news clustering, narrative mapping, and advanced NLP techniques for improved narrative coherence, enhanced thematic clarity, and effective sentiment analysis. By advancing the science of market storytelling, this approach provides investors, analysts, and policymakers with actionable insights, enhancing their ability to anticipate market shifts, manage financial risks, and maintain market stability.
References
1. Antolín-Díaz, Juan, and Juan F. Rubio-Ramírez. (2018) Narrative Sign Restrictions for SVARs. American Economic Review 108 (10): 2802–29. https://www.doi.org/10.1257/ aer.20161852
2. Bhargava R., Lou X., Ozik G., Sadka R., Whitmore T. (2023) Quantifying Narratives and their Impact on Financial Markets. Journal of Portfolio Management, 49 (5) 82-95 http://dx.doi.org/10.2139/ssrn.4166640
3. Brian F. K. N., Tanushree M. (2021) Narrative Maps: An Algorithmic Approach to Represent and Extract Information Narratives Proceedings of the ACM on Human-Computer Interaction, Volume 4, Issue CSCW3 Article No.: 228, Pages 1 – 33 https://doi.org/10.1145/3432927
4. Damodaran A. (2017). Narrative and Numbers: The Value of Stories in Business. Columbia University Press. https://doi.org/10.7312/damo18048
5. Deveikyte J., Geman H., Piccari C., Provetti A. (2022) A sentiment analysis approach to the prediction of market volatility. Front. Artif. Intell. 5:836809. https://doi.org/10.3389/frai.2022.836809
6. Fisher W. R. (1984) The Narrative Paradigm: in the Beginning, Journal of Communication, Volume 34, Issue 1, Pages 74–87, https://doi.org/10.1111/j.1460-2466.1984.tb02986.x
7. Goetzmann W. N., Kim D., Shiller R. J., (2022) Crash Narratives. NBER Working Paper No. w 30195, OFR 23-10, https://ssrn.com/abstract=4153089
8. Hayrapetyan D., Melkumyan H (2024). Noisy Trader Behavior in Adaptive Markets: Decision-Making Biases and Modeling Approaches. «Bulletin of Yerevan University G: Economics» Vol. 16, N2 (24), 2024թ., էջ. 57-66 https://doi.org/10.46991/BYSU.G/ 2024.15.2.057
9. James, N., & Menzies, M. (2023). An exploration of the mathematical structure and behavioural biases of 21st century financial crises. Physica A: Statistical Mechanics and its Applications, 630, 129256. https://doi.org/10.1016/j.physa.2023.129256
10. Mangee N. (2021) How Novelty and Narratives Drive the Stock Market: Black Swans, Animal Spirits and Scapegoats. Cambridge: Cambridge University Press.
11. Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
12. Parida, L., & Ramakrishnan, N. (2005). Redescription mining: Structure theory and algorithms. In Proceedings of the 20th National Conference on Artificial Intelligence (pp. 837–843). AAAI Press.
13. Roos M., Reccius M. (2023) Narratives in economics. Journal of Economic Surveys,1–39. https://doi.org/10.1111/joes.12576
14. Shiller R. J. (2019) Narrative Economics: How Stories Go Viral and Drive Major Economic Events. Princeton University Press. https://doi.org/10.2307/j.ctvdf0jm5
15. Taffler R. J., Agarwal V., Obring M. (2024) Narrative Emotions and Market Crises, Journal of Behavioral Finance, https://doi.org/10.1080/15427560.2024.2365723
16. Tetlock P. C. (2007) Giving Content to Investor Sentiment: The Role of Media in the Stock Market. Journal of Finance, Forthcoming. http://dx.doi.org/10.2139/ssrn.685145
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Davit Hayrapetyan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
