Designing an Assistant for the Disclosure and Management of Information about Needs and Support: the ADMINS project

Abstract

In this paper, we describe accessible design considerations for the Assistants for the Disclosure and Management of Information about Needs and Support project (ADMINS). In ADMINS, artificial intelligence (AI) services are being used to create a virtual assistant (VA), which is being designed to enable students to disclose any disabilities, and to provide guidance and suggestions about appropriate accessible support. ADMINS explores the potential of a conversational user interface (CUI) to reduce administrative burden and improve outcomes, by replacing static forms with written and spoken dialogue. Students with accessibility needs often face excessive administrative burden. A CUI could be beneficial in this context if designed to be fully accessible. At the same time, we recognise the broader potential of CUIs for these types of processes, and the project aims to understand the multiple opportunities and challenges, using participatory design, iterative development and trials evaluations. CCS CONCEPTS• Computing methodologies → Intelligent agents; • Information systems → Expert systems; • Social and professional top-ics → People with disabilities.

Implementing an accessible conversational user interface

“…Most participants had prior experience of interacting with CUIs, using text or combination of speech and text (Table 2). The devices mostly utilised by students in their interactions included laptops (18), mobile phones (14), tablet (10) and desktop computer (6) with a predominance of Microsoft Windows (20) and equal use of Android and Apple's iOS (10). Google Chrome was the most extended browser (15) followed by Internet Explorer and Edge (9).…”

“…This involves working with students to understand their accessibility needs and preferences and working with disability support advisors as expert stakeholders. Student consultants have been employed to provide substantial guidance to the project and take part in ad-hoc testing, and this is supplemented with workshops and formal trials with students who have diverse accessibility needs [10]. Disability support advisors have also been involved as expert stakeholders throughout the project, thus ensuring that the assistant is designed to support the disability advisor role and not replace it.…”

Taylor, the Disability Disclosure Virtual Assistant: A Case Study of Participatory Research with Disabled Students

“…Again, literature supports this; critiquing closed questions as 'unhelpful' [42] and advocating for more discursive, conversational approaches [10,42]. In this study, in partnership with students, we have been able to move beyond the static open questions in forms to a more truly conversational approach, which was received positively by students in the beta trial [46]. This was primarily due to the meaningful and ongoing nature of participation with disabled students over the phases of the project, as many of these issues would not have arisen sufficiently if the participation was limited to discretized, one-off workshops, or consultations.…”

Educational Technology Research: Contexts, Complexity and Challenges

“…One example of this is the current Assistants for the Disclosure and Management of Information about Needs and Support project (ADMINS). This project is taking an artificial intelligence (AI) approach to the design of a virtual assistant (VA), to reduce the administrative burden on students to disclose any disabilities, and allow accessible support to be offered (Iniesto et al 2020).…”