Computational Assistance for User Interface Design: Smarter Generation and Evaluation of Design Ideas

Abstract

This paper describes a lab demo by the User Interfaces group at Aalto University. The demo allows attendees to interactively experience recent research prototypes aiming to facilitate designers’ creative and problem-solving capabilities in user interface (UI) design. Empirical work on designers suggests that UI design is challenging, partially because of the presence of very large design spaces, multiple and ill-defined objectives, design fixation and biases, as well as multiple requirements that need to to kept in mind. At the exhibition, members of the lab provide live demonstrations of six computational features, with a special focus on plug-ins created for Figma, a popular UI design tool. The demos draw from the group’s latest research published at HCI conferences. They demonstrate how to interactively exploit machine learning methods ranging from deep nets to Bayesian inference and NLP. We also present our design approach and provide a summary of findings from empirical evaluations with designers.