Can Language Predict Bankruptcy? The Explanatory Power of Tone in 10‐K Filings

Abstract

We examine whether the language used in 10-K filings reflects a firm's risk of bankruptcy. Our sample contains 424 bankrupt U.S. companies in the period 1994-2015 and we use propensity score matching to find healthy matches. Based on a logit model of failing and vital firms, our findings indicate that firms at risk of bankruptcy use significantly more negative words in their 10-K filings than comparable vital companies. This relationship holds up until three years prior to the actual bankruptcy filing. With our investigation, we confirm the results from previous accounting and finance research. 10-K filings contain valuable information beyond the reported financials. Additionally, we show that 10-Ks filed in the year of a firm's collapse contain an increased number of litigious words relative to healthy businesses. This indicates that the management of failing firms is already dealing with legal issues when reporting financials prior to bankruptcy. Our results suggest that analysts ought to include the presentation of financials in their assessment of bankruptcy risk as it contains explanatory and predictive power beyond the financial ratios.Les auteurs se demandent si le langage utilis e dans les d eclarations 10-K r ev ele l'existence d'un risque de faillite de l'entreprise. Ils analysent un echantillon de 424 soci et es des Etats-Unis ayant fait faillite entre 1994 et 2015 et utilisent l'appariement des coefficients de propension pour d eterminer quelles sont les correspondances d'entreprises saines. En appliquant un mod ele logit aux entreprises d efaillantes et aux entreprises saines, ils constatent que celles qui pr esentent un risque de d efaillance font un usage sensiblement plus abondant de termes n egatifs dans leurs d eclarations 10-K que les entreprises saines comparables. Cette relation perdure jusqu' a trois ans avant le r eel d epôt de bilan. L' etude confirme les * Accepted by Pascale Lapointe-Antunes.

Do auditors price litigious tone?

“…There are on average 472 litigious words (LIT_NUM_10K t−1 ) used in 10-K reports, representing an average of about 0.67 percent 4 of total average words in 10-K reports of our sample firms. The percentage of litigious words in our sample firms is considerably lower than the percentage of 2.08 percent reported by Lopatta et al (2017) for bankrupt firms from 1993 to 2013. This suggests that failing firms face significantly more legal issues compared with healthy firms (Lopatta et al, 2017).…”

“…The percentage of litigious words in our sample firms is considerably lower than the percentage of 2.08 percent reported by Lopatta et al . (2017) for bankrupt firms from 1993 to 2013. This suggests that failing firms face significantly more legal issues compared with healthy firms (Lopatta et al ., 2017).…”

“…(2017) for bankrupt firms from 1993 to 2013. This suggests that failing firms face significantly more legal issues compared with healthy firms (Lopatta et al ., 2017). The average values of other tonal variables ( POSNEG_NUM_10K t −1 , UNCERTAIN_NUM_10K t −1 , MODAL_S_NUM_10K t −1 and MODAL_W_NUM_10K t −1 ) and disclosure characteristics ( SMOG_10K t −1 and WORDS_10K t −1 ) are consistent with prior studies (e.g., Ertugrul et al ., 2017; Bakarich et al ., 2019).…”

Optimistic tone and audit fees: Some Australian evidence

“…The sentiment (i.e., tone) of messages reflected in annual reports (Henry, 2008;Huang et al, 2014;Yekini, Wisniewski, & Millo, 2016) tends to influence investors' and analysts' views about firms. Similarly, one can argue that annual report tone would be associated with audit risk assessment (see Lopatta, Gloger, & Jaeschke, 2017;Yang, Yu, Liu, & Wu, 2018), as, for example, auditing standards require auditors' perusal of information that accompanies audited financial statements (International Federation of Accountants, 2012). Nevertheless, whether the overall tone reflected in the reports is associated with auditor's decisions remains yet to be empirically examined.…”

Bankruptcy prediction using disclosure text features

“…They found that the annual report's more negative sentiment is associated with larger delisting probabilities, lower odds of paying subsequent dividends, higher subsequent loan loss provisions, and lower future return on assets. Similarly, Lopatta, Gloger, and Jaeschke (2017) concluded that firms at risk of bankruptcy use significantly more negative words in their 10-K filings than comparable vital companies. This relationship holds up until three years before the actual bankruptcy filing.…”