Date of Award
Doctor of Philosophy (PhD)
Michael J. Paul
James H. Martin
Machine learning is ubiquitous in making predictions that affect people's decisions. While most of the research in machine learning focuses on improving the performance of the models on held-out data sets, this is not enough to convince end-users that these models are trustworthy or reliable in the wild. To address this problem, a new line of research has emerged that focuses on developing interpretable machine learning methods and helping end-users make informed decisions.
Despite the growing body of research in developing interpretable models, there is still no consensus on the definition and quantification of interpretability. We argue that to understand interpretability, we need to bring humans in the loop and run human-subject experiments to understand the effect of interpretability on human behavior. This thesis approaches the problem of interpretability from an interdisciplinary perspective which builds on decades of research in psychology, cognitive science, and social science to understand human behavior and trust. Through controlled user experiments, we manipulate various design factors in supervised models that are commonly thought to make models more or less interpretable and measure their influence on user behavior, performance, and trust. Additionally, we develop interpretable and interactive machine learning based systems that exploit unsupervised machine learning models to bring humans in the loop and help them in completing real-world tasks. By bringing humans and machines together, we can empower humans to understand and organize large document collections better and faster. Our findings and insights from these experiments can guide the development of next-generation machine learning models that can be used effectively and trusted by humans.
Poursabzi-Sangdeh, Forough, "Design and Empirical Evaluation of Interactive and Interpretable Machine Learning" (2018). Computer Science Graduate Theses & Dissertations. 163.