We conducted four studies to explore the effects of transparency, control, and the interaction between the two on user experience and system performance. We first explored control and transparency in supervised machine learning, where most prior research efforts have focused. We evaluated the effects of specific feedback and explanation mechanisms on user experience and feedback quality with a simple text classifier. Explanations and feedback together resulted in the highest user satisfaction and system performance, and users' satisfaction decreased when given explanations without means for feedback.
We then switched the focus to unsupervised machine learning, in particular, topic models, to explore transparency and control in the context of more complex models and subjective tasks. Here, first, we developed a novel visualization technique for topic transparency and compared it against common topic representations for interpretability. While a simple word list visualization supported users in quickly understanding topics, our visualization exposed phrases that other representations obscured.
Next, we developed a novel "human-centered" interactive topic modeling system that was both transparent and interactive, based on the optimal topic representations and users' desired control mechanisms identified by our prior work. We conducted a formative study of user experience with our interactive topic modeling system. This study identified two aspects of control exposed by transparency: adherence, or whether models incorporate user feedback as expected, and stability, or whether other unexpected model updates occur.
Finally, we further studied adherence and stability by comparing user experience with our interactive topic modeling system across three algorithm variants. These variants differed in how user input was incorporated into the model, which resulted in differences in how the model adhered to user input, the model's stability between updates, update latency, and the coherence of the generated topics. Participants disliked slow updates the most, followed by the lack of adherence, but across modeling approaches, participants differed only in whether they noticed adherence. In both the formative and comparative interactive topic modeling studies, participants were polarized by instability: some liked it when it resulted in model improvements, whereas others preferred more control. This dissertation contributes to our understanding of how end users comprehend and interact with machine learning models and provides guidelines for designing systems for the "human in the loop."
Examining Committee:
Co-Chair: Dr. Leah Findlater
Dean's rep: Dr. Naomi Feldman
Members: Dr. Mihai Pop
Dr. Hernisa Kacorri
Alison Smith-Renner is a Ph.D. candidate in the Department of Computer Science at the University of Maryland, College Park, where she received her M.S. in Computer Science in 2014. She also leads the Machine Learning Visualization Lab for Decisive Analytics Corporation, where she designs user interfaces and visualizations for interacting with intelligent systems and their results.
Her research interests lie at the intersection of machine learning and human-computer interaction, with a particular focus on enhancing users' understanding and interaction with machine learning without requiring prior expertise. She is active in the explainable machine learning and human-centered machine learning communities.
She received her B.S. in Applied Mathematics with a minor in Computer Science from The College of William and Mary in 2009.