Journal article · 2026 · Open access
Financial statement fraud detection using topic-driven financial sentiment analysis
Decision Support Systems, 203, 114615 · Published 8 January 2026 · DOI 10.1016/j.dss.2026.114615
In brief
“Financial statement fraud detection using topic-driven financial sentiment analysis” is a 2026 journal article by Petr Hajek and 2 co-authors, published in Decision Support Systems. OpenAlex counts 13 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Decision Support Systems.
- Citations
- 13
- Most cited in
- 2026 (12)
- Field-weighted impact
- 71.45
- References
- 44
- Authors
- 3
Abstract
Financial statement fraud undermines market integrity and incurs substantial costs for investors, regulators, and companies. Text-based detection methods have emerged as useful complements to traditional financial indicators, but many fail to incorporate domain-specific topics or sentiment cues, often missing subtle changes in deceptive communication. To overcome this problem, this study proposes a topic-driven financial sentiment analysis (TDFSA) model that detects corporate fraud by analyzing linguistic patterns in the Management Discussion & Analysis (MD&A) sections of annual reports. Our approach captures contextual sentiment within financially relevant topics using FinBERT embeddings. To evaluate these signals in fraud detection, we integrate the TDFSA outputs into a broader cost-sensitive evaluation framework. This framework combines text-based indicators with financial ratios to balance the need to avoid false alarms with the high cost of undetected fraud. Using data from U.S. firms flagged in SEC Accounting and Auditing Enforcement Releases from 2014 to 2024 and matched non-fraud peers, we examine trends in financial ratios, textual complexity, and sentiment dynamics in the three years preceding fraud events. The results show that models leveraging TDFSA achieve higher detection accuracy and lower cost than dictionary-based sentiment, generic topic models, and deep learning baselines. • Topic-driven financial sentiment analysis (TDFSA) improves financial statement fraud detection. • FinBERT embeddings capture both topic-level and sentiment context in MD&A disclosures. • Cost-sensitive learning prioritizes preventing undetected fraud over false alarms, using a 6.46:1 ratio. • The proposed model provides accurate and fair decision support for auditors and investors.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hajek, P., Novotný, J., & Munk, M. (2026). Financial statement fraud detection using topic-driven financial sentiment analysis. Decision Support Systems, 203, 114615. https://doi.org/10.1016/j.dss.2026.114615
MLA 9
Hajek, Petr, et al. “Financial statement fraud detection using topic-driven financial sentiment analysis.” Decision Support Systems, vol. 203, 2026, p. 114615. https://doi.org/10.1016/j.dss.2026.114615.
Chicago
Hajek, Petr, Josef Novotný, and Michal Munk. 2026. “Financial statement fraud detection using topic-driven financial sentiment analysis.” Decision Support Systems 203: 114615. https://doi.org/10.1016/j.dss.2026.114615.
Harvard
Hajek, P., Novotný, J. and Munk, M. (2026) ‘Financial statement fraud detection using topic-driven financial sentiment analysis’, Decision Support Systems, 203, p. 114615. doi:10.1016/j.dss.2026.114615.
IEEE
P. Hajek, J. Novotný, and M. Munk, “Financial statement fraud detection using topic-driven financial sentiment analysis,” Decision Support Systems, vol. 203, p. 114615, 2026, doi: 10.1016/j.dss.2026.114615.
BibTeX
@article{hajek2026financial,
title = {{Financial statement fraud detection using topic-driven financial sentiment analysis}},
author = {Hajek, Petr and Novotný, Josef and Munk, Michal},
journal = {Decision Support Systems},
year = {2026},
volume = {203},
pages = {114615},
doi = {10.1016/j.dss.2026.114615},
url = {https://doi.org/10.1016/j.dss.2026.114615}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Business, Management and Accounting › Accounting › Auditing, Earnings Management, Governance
- financial statement fraud detection
- management discussion and analysis
- annual report disclosure
- cost-sensitive learning
- financial ratios
Work with this paper
Most-cited papers in Business, Management and Accounting
- Firm Resources and Sustained Competitive AdvantageJay Bryan Barney · Journal of Management · 1991 · 57,081 citations
- The Iron Cage Revisited: Institutional Isomorphism and Collective Rationality in Organizational FieldsPaul DiMaggio, Walter W. Powell · American Sociological Review · 1983 · 42,816 citations
- Building Theories from Case Study ResearchKathleen M. Eisenhardt · Academy of Management Review · 1989 · 39,809 citations
- Firm resources and sustained competitive advantageJay Bryan Barney · Advances in strategic management · 2004 · 38,183 citations
- Absorptive Capacity: A New Perspective on Learning and InnovationWesley M. Cohen, Daniel A. Levinthal · Administrative Science Quarterly · 1990 · 37,030 citations
Questions about this paper
How do I cite this paper in APA style?
Hajek, P., Novotný, J., & Munk, M. (2026). Financial statement fraud detection using topic-driven financial sentiment analysis. Decision Support Systems, 203, 114615. https://doi.org/10.1016/j.dss.2026.114615
How many times has this paper been cited?
13 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Decision Support Systems: sign in and open the full text from this page.
Who wrote this paper?
Petr Hajek, Josef Novotný, Michal Munk.
What is the DOI of this paper?
10.1016/j.dss.2026.114615, permanently at https://doi.org/10.1016/j.dss.2026.114615. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.