Date of Award:

12-2025

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Computer Science

Committee Chair(s)

Vicki Allan

Committee

Vicki Allan

Committee

John Edwards

Committee

Vladimir Kulyukin

Abstract

Many researchers have investigated the factors influencing software developer workplace outcomes, such as job satisfaction, due to the central role of the tech industry in the global economy and the specialized expertise of software developers. Past research has often relied on small surveys and traditional analysis methods, with limited use of modern machine learning techniques. This study introduces an efficient and scalable approach to analyzing software developer job satisfaction using interpretable machine learning.

We use data from the 2019 and 2024 Stack Overflow Developer Surveys, an annual survey of software developers worldwide that encompasses a broad range of topics, including demographics, technology usage, and workplace experiences. We experiment with machine learning classification models to predict job satisfaction and interpret results using SHAP (Shapley Additive Explanations), a method for understanding model decision-making.

We find that key job satisfaction predictors for these datasets include how developers feel about their support from managers, work environment, and company resources, and that many factors interact in complex ways. We also find that demographic characteristics, such as gender, race, and years of experience, are often more impactful predictors for minority subgroups and that some of the same factors contribute to high job satisfaction predictions during one year and low job satisfaction predictions during the other year, which may be related to industry changes resulting from the COVID-19 pandemic. Overall, our results uncover actionable insights into software developer job satisfaction, highlight the potential for interpretable machine learning methods to support informed decision-making in the tech workplace, and identify patterns that could be the focus of future work.

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .