Open Language Chief Executive Personality Tool (OLCPT)

The Open Language Chief Executive Personality Tool (OLCPT) is a natural language processing (NLP) application that was developed to estimate personality scores of U.S. public company executives based on their language use. It works by reading in texts of executives’ speech from a comma-delimited (.csv) file or a set of plain text (.txt) files, and then applying machine learning (ML) models to estimate the executives’ personality traits. The current version provides estimates of executives’ personality traits from the Five Factor Model (FFM) of personality (i.e., openness to experience, conscientiousness, extraversion, agreeableness, and neuroticism, Costa & McCrae, 1985) as well as narcissism and humility. Traits are scored on a scale from 1 to 7, where 1 indicates low values and 7 indicates high values for each trait.

Tool Development

The program is based on ML models developed and validated by Harrison and colleagues (2019, 2020, 2024). It was trained by identifying key features of CEOs’ language in their responses during the Q&A section of earnings calls with equity analysts and comparing those with valid ratings of the CEOs' personality traits.

The training data for the current version include videometric and historiometric scores that were graciously provided by Benischke et al. (2019), Gupta et al. (2018), and Hill et al. (2019). Detail on the videometric and historiometric procedures used by those authors can be found in their papers. (See the ReadMe for full citations).

Use Guidelines

Use of the OLCPT is free and available to the public for research or educational purposes under the Open Data Commons Attribution License. We ask that authors who use the data (1) cite the articles developing and validating the tool and (2) reference the specific version number that their paper employed.

The tool has been shown to be valid and reliable for predicting personality traits of S&P 1500 executives from their language use in the Q&A section of quarterly earnings calls with equity analysts. Thus, unless it is validated for use in different contexts in the future, it should only be used to assess the personality traits of top executives of public, U.S. companies.

By downloading the OLCPT, you agree to use this program solely for research or educational purposes. Please contact the lead author if you intend to use the tool for commercial purposes.

Recommended Citations

(1)   Harrison, J. S., Thurgood, G. R., Boivie, S., & Pfarrer, M. D. 2019. Measuring CEO personality: Developing, validating, and testing a linguistic tool. Strategic Management Journal, 40(8): 1316-1330.

(2)   Harrison, J. S., Thurgood, G. R., Boivie, S., & Pfarrer, M. D. 2020. Perception is reality: How CEOs’ observed personality influences market perceptions of firm risk and shareholder returns. Academy of Management Journal, 63(4): 1166-1195.

(3)   Harrison, J. S., Boivie, S., Hubbard, T. D., & Petrenko, O. V. 2024. Executive personality assessment with large language models: Updating an existing tool and advancing similar measures in strategy and management research. Forthcoming at Research Methods in Strategy and Management.

Note: To cite appendices, we recommend using the convention, “(see Appendix X in Harrison et al, XXX)”, with the full paper citation in the References section.