When Positive Sentiment Is Not So Positive: Textual Analytics and Bank Failures

We extend beyond healthiness assessment of banks using quantitative financial data by applying textual sentiment analysis. Looking at 10-K annual reports for a large sample of banks in the 2000-2014 period, 52 public bank holding companies that were associated with bank failures during the global financial crisis serve as a natural experiment. Utilizing negative and positive dictionaries proposed by Loughran and McDonald (2011), we find that both sentiments on average discriminate between failed and non-failed banks 80% of the time. However, we find that positive sentiment contains stronger predictive power than negative sentiment; out of ten failed banks, on average positive sentiment can identify seven true events, whereas negative sentiment identifies five failed banks at most. While one would link financial soundness with more positive sentiment, it appears that failed banks exhausted more positive sentiment than their non-failed peers, whether ex-ante in anticipation of good news or ex-post to conceal