Off-campus Eastern Washington University users: To download EWU Only theses, please use your EWU SSO (Single Sign-on) credentials. Clicking the blue “Download” button below will prompt you to log in in order to access the thesis document.

Non-EWU users: Please talk to your local librarian about requesting this thesis through Interlibrary loan.

Date of Award

Spring 2025

Rights

Access perpetually restricted to EWU users with an active EWU NetID

Document Type

Thesis: EWU Only

Degree Name

Doctorate of Education (EdD) in Educational Leadership

Department

Education

Abstract

This study examined computational approaches to leadership trait assessment through verbal behavior analysis using machine learning algorithms applied to the Psychological Characteristics of Leaders (PsyCL) dataset. Seven algorithms were evaluated for their ability to predict leadership traits across 14 trait dimensions from verbal features. Results showed strong prediction capability (R² = 0.69-0.90), with tree-based methods (Random Forest, Gradient Boosting) consistently outperforming linear models across all traits. Prediction accuracy varied significantly, with task orientation and conceptual complexity showing stronger predictability than self-confidence dimensions. The findings suggest that computational approaches may effectively complement traditional leadership assessment methods by enhancing measurement scale and consistency, while potentially reducing assessor bias. These results contributed to leadership theory by providing empirical support for verbalizing leadership traits while identifying optimal computational approaches for capturing trait-behavior relationships. Practical applications included enhanced leadership development systems integrating computational assessment within established frameworks.

Download

Share

COinS