How informative is the text of securities complaints?

Abstract

Much of the research in law and finance reduces complex texts down to a handful of variables. Legal scholars have voiced concerns that this dimensionality reduction loses important detail that is embedded in legal text. This article assesses this critique by asking whether text analysis can capture meaningful predictive information. It does so by applying text analysis and machine learning to a corpus of private securities class action complaints that contains over 90 million words. This analysis produces three primary findings: (1) the best performing models predict outcomes with an accuracy rate of about 70%, which is higher than baseline rates; (2) a hybrid model that uses both text and nontext components performs better than either of these two components alone; and (3) the predictions made by the machine learning models are associated with substantial abnormal returns in the days after cases get filed (JEL G10, G14).

The merits of securities litigation and corporate reputation

“…Carrizosa and Cazier (2022) find that these allegations are associated with larger filing date returns, consistent with them providing new information to the market. Badawi (2023) similarly finds the existence of “hard facts” in the complaints helps predict future case outcomes. We then examine how these measures are associated with reputational damage and case merits.…”

“…Hall (1993, p. 616) states that reputation “is a fragile resource.” Shapira (2019, p. 875) notes that litigation may affect reputation by exposing information to the “public, thereby reducing the willingness of outside observers to trust and do business” with a firm. Carrizosa and Cazier (2022) and Badawi (2023) validate this mechanism by showing that litigation filings contain value‐relevant information. Litigation may also strengthen the credibility of other bad news and increase scrutiny.…”

“…Plaintiffs must now plead specific facts that support a strong inference of fraud (Perino, 2003). Thus, filings reveal and summarize adverse firm information, such as detailed misconduct allegations and systematic governance and control inadequacies (Badawi, 2023; Carrizosa & Cazier, 2022).…”