WPI – Computer Science
Thursday, April 25, 2019
Time: 2:00 p.m. – 3:00 p.m.
Location: Fuller Labs B16
Advisor: Prof. Erin Solovey
Reader: Prof. Lane Harrison
Many intelligent systems can be personalized by end-users to suit their specific needs. However, the interface for personalization often trades off the degree of personalization achievable with time, effort, and level of expertise required by the user.
We explore two approaches to end-user personalization: one asks the user to manually specify the system's desired behavior using an end-user programming language, while the other only asks the user to provide feedback on the system's behavior to train the system using reinforcement learning.
To understand the advantages and disadvantages of each approach, we conducted a comparative user study. We report participant attitudes towards each and discuss the implications of choosing one over the other.