Textual Analysis in Financial Disclosures

Textual analysis has emerged as a crucial discipline within accounting and finance, offering a means to extract meaningful information from narrative corporate reports. Advances in natural language processing and machine learning enable researchers to quantify tone, sentiment, readability and thematic structure within annual reports, earnings calls and regulatory filings. Such methods reveal how firms communicate risk, strategic priorities and ethical commitments to stakeholders. By converting unstructured text into measurable variables, scholars have linked the linguistic attributes of disclosures to firm valuation, earnings management, governance quality and market reactions across jurisdictions. The growing availability of digitised financial reports has supported large‐scale studies that inform regulatory debate and corporate practice, from detecting earnings manipulation to assessing the spillover effects of sustainable strategy narratives in supply chains. The global scope of textual analysis underscores its potential to improve transparency and decision‐making in diverse regulatory environments.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Textual Analysis in Financial Disclosures publication trend

The graph below shows the total number of articles in textual analysis in financial disclosures across all publications each year (not limited to Nature Index journals).

Technical terms

Textual analysis: The systematic process of converting unstructured text into quantitative metrics for research or decision‐making.

Natural language processing (NLP): A subfield of artificial intelligence focused on enabling computers to understand, interpret and generate human language.

Sentiment analysis: The automated assessment of emotional tone, classifying text as positive, negative or neutral to infer attitudes or intentions.

Dictionary‐based approach: A method that relies on predefined word lists to categorise text according to themes, sentiment or regulatory concepts.

Latent Dirichlet allocation (LDA): A statistical topic‐modelling technique that identifies underlying thematic structures within large text corpora.

Tone: The overall linguistic tenor of a disclosure, reflecting optimism, caution or formality, which may influence stakeholder perceptions.

References

1. The tone of buyer firms' annual reports and suppliers' green innovation: The spillover effects in the supply chain. Business Strategy and the Environment (2024).
2. In search of meaning: Lessons, resources and next steps for computational analysis of financial discourse. Journal of Business Finance &amp Accounting (2019).
3. Fad or future? Automated analysis of financial text and its implications for corporate reporting. Accounting and Business Research (2019).
4. Board characteristics and negative disclosure tone. Journal of Accounting Literature (2022).
5. Tone of language, financial disclosure, and earnings management: a textual analysis of form 20-F. Financial Innovation (2022).
6. Narrative disclosure tone: A review and areas for future research. Journal of International Accounting Auditing and Taxation (2022).