Journals / Yalova Sosyal Bilimler Dergisi / 2026 / Cilt: 16 Sayı: 1

A Crisis that Began with a Tweet: Temporal and Thematic Analysis of Social Media Sentiment Dynamics in Financial Collapse Processes

Bir Tweet ile Başlayan Kriz: Finansal Çöküş Süreçlerinde Sosyal Medya Duygu Dinamiklerinin Zamansal ve Tematik Analizi

İrfan Kahraman(ISTANBUL UNIVERSITY)
Emrah Önder(İSTANBUL ÜNİVERSİTESİ)0000-0002-0554-1290
Pages
88–110
Publication Date
2026-04-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The findings indicate a significant increase in negative sentiment intensity immediately prior to the crisis.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The series of bank failures in the United States in 2023, particularly the collapse of Signature Bank, revealed the fragility of the financial system and produced profound effects not only on economic indicators but also within digital social domains.
📊
Key Findings & Data:This study investigates the reflections of financial crises on social media platforms and to demonstrate how users’ perceptions of crises can be evaluated through sentiment analysis methods.
💡
Conclusion & Impact:The findings indicate a significant increase in negative sentiment intensity immediately prior to the crisis.
🔬Design:Modeling & Simulation
📍Scope:2023 Verileri
⚙️Variables:İşletme · Finansal Krizler · Sosyal Medya Verileri

Abstract

The series of bank failures in the United States in 2023, particularly the collapse of Signature Bank, revealed the fragility of the financial system and produced profound effects not only on economic indicators but also within digital social domains. This study investigates the reflections of financial crises on social media platforms and to demonstrate how users’ perceptions of crises can be evaluated through sentiment analysis methods. To this end, data collected from microblogging platforms were analyzed using natural language processing-based sentiment analysis models, namely VADER and FinBERT. The findings indicate a significant increase in negative sentiment intensity immediately prior to the crisis. This result suggests that the surge in negative discourse can be considered an early warning indicator of crisis perception among social media users. Moreover, the outcomes reveal that sentiment analysis is not limited to post-crisis evaluations but can also be applied effectively in the pre-crisis period for early detection. The study emphasizes that text mining techniques represent an innovative tool for identifying financial collapses in advance and highlights how social media data can serve as a strategic instrument in crisis management, social trust analysis, and financial decision-support systems. In this respect, the research contributes to both the finance literature and digital communication studies.

Özet

2023 yılında ABD’de yaşanan banka iflasları, özellikle Signature Bank’ın çöküşü, finansal sistemin kırılganlığını gözler önüne sermiş ve yalnızca ekonomik göstergeler üzerinde değil, aynı zamanda dijital sosyal alanlarda da derin etkiler yaratmıştır. Bu çalışmanın amacı, finansal krizlerin sosyal medya platformlarındaki yansımalarını incelemek ve kullanıcıların kriz algılarının duygu analizi yöntemleri aracılığıyla nasıl değerlendirilebileceğini ortaya koymaktır. Bu doğrultuda, mikroblog içeriklerinden elde edilen veriler doğal dil işleme tabanlı duygu analizi yöntemleri olan VADER ve FinBERT modelleriyle analiz edilmiştir. Bulgular, krizden hemen önce olumsuz duygu yoğunluğunda belirgin bir artış yaşandığını göstermektedir. Bu bulgu, sosyal medya kullanıcılarının kriz algısına ilişkin erken uyarı işareti olarak değerlendirilebilecek niteliktedir. Ayrıca, elde edilen veriler, duygu analizinin yalnızca kriz sonrası dönemde değil, krizlerin ortaya çıkmasından önce de kullanılabileceğini göstermektedir. Çalışma, metin madenciliği tekniklerinin finansal krizlerin erken tespiti için yenilikçi bir araç olduğunu vurgulamakta, aynı zamanda sosyal medya verilerinin kriz yönetimi, toplumsal güven analizi ve finansal karar destek sistemlerinde stratejik olarak kullanılabileceğini ortaya koymaktadır. Bu yönüyle araştırma hem finans literatürüne hem de dijital iletişim çalışmalarına katkı sağlamaktadır.

🔖

Cite This Article

Kahraman, İ., Önder, E. (2026). A Crisis that Began with a Tweet: Temporal and Thematic Analysis of Social Media Sentiment Dynamics in Financial Collapse Processes. Yalova Sosyal Bilimler Dergisi, Cilt: 16 Sayı: 1, 88–110. https://doi.org/10.17828/yalovasosbil.1785839

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (33)

  1. Balcıoğlu, Yavuz Selim. “Analyzing Customer Sentiments and Trends in Turkish Mobile Banking Apps: A Text Mining Study”. Dumlupınar Üniversitesi Sosyal Bilimler Dergisi 80 (2024), 49-69. https://doi.org/10.51290/dpusbe.1391631
  2. Banerjee, Abhijit V. “A Simple Model of Herd Behavior”. The Quarterly Journal of Economics 107/3 (1992), 797-817. https://doi.org/10.2307/2118364
  3. Barberis, Nicholas vd. “A Model of Investor Sentiment”. Journal of Financial Economics 49/3 (1998), 307-343.
  4. Bivol, Dmitri. Duygu Tahmini İçin Duygu Analizi ve Makine Öğrenmesi. Sakarya: Sakarya Üniversitesi Fen Bilimleri Enstitüsü, Tezsiz Yüksek Lisans Ödevi, 2024.
  5. Bollen, Johan vd. “Twitter Mood Predicts the Stock Market”. Journal of Computational Science 2/1 (2011), 1-8. https://doi.org/10.1016/j.jocs.2010.12.007
  6. Boyd, John H. - Gertler, Mark. “Are Banks Dead? Or Are the Reports Greatly Exaggerated?”. Federal Reserve Bank of Minneapolis Quarterly Review 18/3 (1994), 2-23. https://doi.org/10.21034/qr.1831
  7. Castells, Manuel. “The Network Society Revisited”. American Behavioral Scientist 67/7 (2023), 940-946.
  8. Cong, Lin William vd. “Tokenomics: Dynamic Adoption and Valuation”. The Review of Financial Studies 34/3 (2021), 1105-1155. https://doi.org/10.1093/rfs/hhaa089
  9. Conlon, Thomas - McGee, Richard. “Safe Haven or Risky Hazard? Bitcoin During the Covid-19 Bear Market”. Finance Research Letters 35 (2020), 101607. https://doi.org/10.1016/j.frl.2020.101607
  10. Devenow, Andrea - Welch, Ivo. “Rational Herding in Financial Economics”. European Economic Review 40/3-5 (1996), 603-615. https://doi.org/10.1016/0014-2921(95)00073-9
  11. Dincer, Elif Şevval vd. “Metin Madenciliği ve Duygu Analizi ile Siber Zorbalık Tespiti”. ESTUDAM Bilişim Dergisi 3/2 (2022), 38-45. https://doi.org/10.53608/estudambilisim.1070884
  12. Du, Kelvin vd. “Financial Sentiment Analysis: Techniques and Applications”. ACM Computing Surveys 56/9 (2024), 1-42. https://doi.org/10.1145/3649451
  13. Duan, Ganglong vd. “A Hybrid Neural Network Model for Sentiment Analysis of Financial Texts Using Topic Extraction, Pre-Trained Model, and Enhanced Attention Mechanism Methods”. IEEE Access 12 (2024), 98207-98218. https://doi.org/10.1109/ACCESS.2024.3429150
  14. Fama, Eugene F. “Efficient Capital Markets: A Review of Theory and Empirical Work”. Journal of Finance 25/2 (1970), 383-417. https://doi.org/10.1111/j.1540-6261.1970.tb00518.x
  15. Gupta, Aaryan vd. “Comprehensive Review of Text-Mining Applications in Finance”. Financial Innovation 6/39 (Aralık 2020), 1-25. https://doi.org/10.1186/s40854-020-00205-1
  16. Li, Jianping vd. “Financial Crises, Bank Risk Exposure and the Efficacy of Government Interventions”. Journal of Banking & Finance 109 (2019), 105654.
  17. Loughran, Tim - McDonald, Bill. “When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks”. The Journal of Finance 66/1 (2011), 35-65. https://doi.org/10.1111/j.1540-6261.2010.01625.x
  18. Mao, Huina vd. “Quantifying the Effects of Online Bullishness on International Financial Markets”. Statistics Paper Series 9 (2015), 1-23.
  19. Martel, Cameron vd. “Reliance on Emotion Promotes Belief in Fake News”. Cognitive Research: Principles and Implications 5 (2020), 47. https://doi.org/10.1186/s41235-020-00252-3
  20. Mishev, Kire vd. “Evaluation of Sentiment Analysis in Finance: From Lexicons to Transformations". IEEE Access 8 (2020), 131662-131682.
  21. Mohammad, Saif M. - Turney, Peter D. “Crowdsourcing a Word-Emotion Association Lexicon”. Computational Intelligence 29/3 (2013), 436-465. https://doi.org/10.1111/j.1467-8640.2012.00460.x
  22. Nasiopoulos, Dimitrios K. vd. “Financial Sentiment Analysis and Classification: A Comparative Study of Fine-Tuned Deep Learning Models”. International Journal of Financial Studies 13/2 (2025), 75. https://doi.org/10.3390/ijfs13020075
  23. Nguyen, Anh H. vd. “The Effect of Dividend Payment on Firm's Financial Performance: An Empirical Study of Vietnam”. Journal of Risk and Financial Management 14/8 (2021), 353. https://doi.org/10.3390/jrfm14080353
  24. Nielsen, Ivan. “Predicting Financial Crises with AI: A Conceptual Framework”. Journal of Artificial Intelligence Research and Applications 4/2 (2024), 94-102.
  25. Tuna, Murat Fatih- Polatgil, Mesut. “Twitter Kullanıcılarının Temettü Yatırımlarında Tercih Ettikleri Şirketlerin Metin Madenciliği ile Tespit Edilmesi”. Dumlupınar Üniversitesi Sosyal Bilimler Dergisi 75 (2023), 24-40. https://doi.org/10.51290/dpusbe.1094979
  26. Pejić-Bach, Mirjana vd. “Text Mining for Big Data Analysis in Financial Sector: A Literature Review”. Sustainability 11/5 (2019), 1277. https://doi.org/10.3390/su11051277
  27. Renault, Thomas. “Sentiment Analysis and Machine Learning in Finance: A Comparison of Methods and Models on One Million Messages”. Digital Finance 2/1-2 (2020), 1-13. https://doi.org/10.1007/s42521-019-00014-x
  28. Shiller, Robert J. “Narrative Economics”. American Economic Review 107/4 (2017), 967-1004. https://doi.org/10.1257/aer.107.4.967
  29. Shin, Jieun vd. “Political Rumoring on Twitter During the 2012 U.S. Presidential Election: Rumor Diffusion and Correction”. New Media & Society 19/8 (2016), 1214-1235. https://doi.org/10.1177/1461444816634054
  30. Tetlock, Paul C. “Giving Content to Investor Sentiment: The Role of Media in the Stock Market”. The Journal of Finance 62/3 (2007), 1139-1168. https://doi.org/10.1111/j.1540-6261.2007.01232.x
  31. Tokcaer, Sümeyye. “Türkçe Metinlerde Duygu Analizi: Yöntemler ve Uygulamalar”. Journal of Yaşar University 16/63 (2021), 1514-1534.
  32. Wang, Ying. “Financial Crisis Prediction Model of Listed Companies Based on Statistics and Artificial Intelligence”. Scientific Programming (2022), 1118023. https://doi.org/10.1155/2022/1118023
  33. Zhang, Yong vd. “Text Mining-Based Analysis of Social Media Data”. Information Systems Frontiers 21 (2019), 1187-1200. https://doi.org/10.1007/s10796-018-9844-5