This paper presents experimental results comparing two different designs for a spoken language interface to email. We compare a mixed-initiative dialogue style, in which users can flexibly control the dialogue, to a systeminitiative dialogue style, in which the system controls the dialogue. Our results show that even though the mixedinitiative system is more efficient, as measured by number of turns, or elapsed time to complete a set of email tasks, users prefer the system-initiative interface. We posit that these preferences arise from the fact that the system initiative interface is easier to learn and more predictable. Keywords Spoken Language Interfaces, Initiative, Email Interfaces
Marilyn A. Walker, Jeanne Fromer, Giuseppe Di Fabb