A Textual Analysis of U.S. Corporate Social Responsibility Reports

We employ computer-based textual analysis to examine disclosure
patterns for a sample of US corporate social responsibility (CSR) reports
from the period 2002–2016. Starting from 466 features commonly used in
computational linguistics, our results show that the linguistics or
disclosure patterns in CSR reports can be used to accurately predict the
actual CSR performance type of CSR reporters. Specifically, we find that
the two most commonly used disclosure characteristics, number of words
and number of sentences, alone can be used to predict reporting firms’
CSR performance type with 81% accuracy. The accuracy of prediction
increases to 96% when the top 50 linguistics features most relevant to
firms’ CSR performance are included in the prediction model. In
addition, we find that the linguistic features of CSR disclosure identified
by our study are incrementally value relevant to investors even after
controlling for the actual CSR performance score from the professional
CSR rating agencies. This finding suggests that the linguistic features of
CSR disclosure can be an important venue for capital market participants
in evaluating firms’ CSR performance type, especially when professional
CSR performance ratings are not available.