There is much excitement about conversation as a new material for design, driven in part by the increased accessibility of voice user interfaces and commoditisation of AI techniques. As part of increased adoption, devices like the Amazon Echo, Google Home and Siri are providing platforms for designers to interact with users in new ways. In spite of this (often hyped) anticipation of an AI-powered future, it is not always clear how the vision measures up to lived reality of ‘having a conversation’ with machines.
In this talk at IxDA’s Interaction ’18, Stuart Reeves offers a window into work being done at the University of Nottingham. He and his colleagues (Martin Porcheron and Joel Fischer) are capturing naturalistic recordings of Echo use in participants’ homes, which enables them to start building a very rich picture of how users actually ‘get stuff done’ with voice UI. In transcribing and analysing recordings in detail, he gets a close and perhaps surprising look at how requests are formulated by users in particular ways that are sensitive to the device and the setting. Conversely, Stuart and his colleagues examine responses produced by voice UI and how, in a range of practical ways, users make them ‘fit into’ the unfolding flow of talk and the broader activities that form the life of the home.
Voice UI and conversation design
About Stuart Reeves
Stuart Reeves is an Assistant Professor and EPSRC Fellow in the School of Computer Science, University of Nottingham, UK. He researches social and collaborative technologies, investigating how people use diverse kinds of interactive devices and systems in real world situations and places. As EPSRC Fellow, he is exploring the connections between academic HCI research and the work of practitioners in UX and technology design professions. Stuart has also authored a book, Designing Interfaces in Public Settings.