Investor Reaction to Financial Disclosures Across Topics: An Application of Latent Dirichlet Allocation

TL;DR

This study uses latent Dirichlet allocation to automatically categorize over 70,000 financial disclosures and analyzes how stock prices respond differently to various topics within these filings.

Contribution

It introduces an automated topic modeling approach to analyze market reactions to regulatory filings across diverse topics, filling a gap in prior research.

Findings

Significant abnormal returns for earnings, credit ratings, and strategic disclosures

Market reactions vary considerably across different disclosure topics

Regulatory filings influence stock valuations differently depending on content

Abstract

This paper provides a holistic study of how stock prices vary in their response to financial disclosures across different topics. Thereby, we specifically shed light into the extensive amount of filings for which no a priori categorization of their content exists. For this purpose, we utilize an approach from data mining - namely, latent Dirichlet allocation - as a means of topic modeling. This technique facilitates our task of automatically categorizing, ex ante, the content of more than 70,000 regulatory 8-K filings from U.S. companies. We then evaluate the subsequent stock market reaction. Our empirical evidence suggests a considerable discrepancy among various types of news stories in terms of their relevance and impact on financial markets. For instance, we find a statistically significant abnormal return in response to earnings results and credit rating, but also for disclosures regarding business strategy, the health sector, as well as mergers and acquisitions. Our results yield findings that benefit managers, investors and policy-makers by indicating how regulatory filings should be structured and the topics most likely to precede changes in stock valuations.