Guidelines for Bimodal Virtual Assistants

Abstract

Multimodality is a widely studied topic that involves communication modes such as speech, writing, gestures, touching, etc. In the field of Conversational User Interfaces, researchers emphasize both advantages and disadvantages in developing either text-based virtual assistants (visual mode) or voice-based virtual assistants (auditory mode) in terms of cognitive effort, memory load, satisfaction, or enjoyment. We also find extant guidelines which are specialized in the development of either text-based or voice-based assistants. However, there is an evident gap in Multimodal Virtual Assistants research, since there are no specific guidelines for the development of Bimodal Virtual Assistants (BVAs) that combine both writing and speech modes. In this paper, we analyze and synthesize those existing guidelines and we propose 22 guidelines sorted into four categories concerning key design issues in the development of virtual assistants with the aim of providing a unified model that helps raise awareness among designers who want to develop BVAs.