For decades, researchers have debated the pros and cons of adaptive user interfaces with enthusiastic AI practitioners often confronting skeptical HCI experts. This paper summarizes the SUPPLE project's six years of work analyzing the characteristics of successful adaptive interfaces and developing efficient algorithms for their automatic generation. We conclude that personalized user interfaces, which are adapted to a person's devices, tasks, preferences and abilities, can improve user satisfaction and performance. Further, we demonstrate that automatic generation of these interfaces is computationally feasible.
Krzysztof Z. Gajos, Daniel S. Weld, and Jacob O. Wobbrock. Decision-theoretic user interface generation. In AAAI'08, pages 1532-1536. AAAI Press, 2008.BibTeX