Cole Short Publishes Research On Evaluating CEO’s Contextual Quality

A critical issue in corporate governance is identifying, rewarding, and retaining high-quality CEOs. But, over time, do evaluators accurately assess a CEO’s contextual quality? Further, which signals may be used to discern this quality?

Dr. Cole Short, Pepperdine Graziadio assistant professor of strategy, along with co-author Timothy Hubbard of the University of Notre Dame, published research exploring this topic for the Academy of Management Discoveries journal. Their paper is one of the first to use a deep learning-based natural language processing (NLP) method to analyze executive speech and its impact on evaluations.

The paper, through two studies, seeks to address long standing questions in assessing a CEO’s contextual quality. In Study 1, Short explores how boards compensate and dismiss CEOs and the media grants awards over time based on contextual quality. The authors then discover that the language spoken by high-and low-quality CEOs on earnings calls differs in the absence of clear performance signals.

In Study 2, Short broadens this analysis by applying a deep learning-based natural language processing model to show that quality corresponds with the content of CEOs’ speech to investors. Specifically the authors show that contextual quality corresponds with a CEO’s “unscripted novelty”, which refers to their tendency to discuss new topics during the unscripted portion of earnings calls.

Read the full study at the Academy of Management Discoveries website.