Do financial performance indicators predict 10-K text sentiments? An application of artificial intelligence

Abstract

In this study, we employ Natural Language Processing (NLP), a subdomain of artificial intelligence (AI), to predict the sentiments while analyzing 3729 annual 10-k financial reports of S&P 500 companies over the 2002–2019 time period. Our findings suggest that the firm's financial performance indicators help reduce negativity in the textual part of 10-ks. In contrast, we do not observe any significant association between the firm's financial performance indicators and 10-ks positivity. Our findings are robust to alternative econometric specifications and alternative measures of key variables. Our results contribute to the accounting and financial disclosure literature by indicating that corporate financial performance indicators can predict the tone of 10-k filings.