Below is a short overview of the methods I use in my linguistic analyses of CEO language.

Data Collection

Earnings calls held by companies listed on US stock markers (e.g. NYSE, NASDAQ, OTC) are commonly transcribed and part of the public record. These transcripts represent the raw materials I use in my research.

One of the main limitations of these transcripts is their unstructured nature; they are plain text documents that cannot be analyzed linguistically as such. I developed an algorithm that converts unstructured transcripts into structured documents I can run queries on. For example, I can analyze how CEOs respond to questions on “Black Lives Matter,” or how CEOs’ opinion on hybrid work has evolved over the months.

CEO Breakdown by Stock Market

I run my analyses on all major stock markets in the United States.

Financial MarketNumber of CEOs

CEO Breakdown by Industry

Industry data is based on the S&P’s Global Industry Classification Standard.

IndustryCEO Count
Information Technology604
Real Estate231
Health Care777
Consumer Discretionary542

CEO Breakdown by Headquarters Location

Countries with fewer than 100 individual CEOs per quarter are removed from analyses.

CountryCEO Count
United States3.094
United Kingdom150