Predictive power of the language for CEO turnovers

Abstract

In this paper, we find novel evidence that the language of the CEO during the earnings calls can predict the upcoming leadership turnover. Specifically, in the meetings preceding the public announcement about the CEO transition, executives exhibit changes in business tone, stress levels, and self-attribution. The results are obtained using a state-of-the-art financial language model, FinBERT, coupled with traditional word-counting algorithms. Our findings suggest that the qualitative information in earnings calls contains signals about the CEO turnover risk incremental to the commonly used quantitative performance variables.