Best Practices for Designing Chatbots in Mental Healthcare – A Case Study on iHelpr

Abstract

This paper outlines the design and development of a chatbot called iHelpr for mental healthcare that 1) administers self-assessment instruments/scales, 2) provides wellbeing and self-help guidance and information, all within a conversational interface. Chatbots are becoming more prevalent in our daily lives, with bots available to provide the user with daily weather forecasts, book holidays, and even converse with a virtual therapist. It is predicted that users may soon prefer to complete tasks using a conversational interface that are traditionally done through a webpage or mobile application. In the context of mental healthcare, demand exceeds supply, waiting lists are ever growing, and populations in rural communities still struggle to access mental healthcare. Chatbots can be utilised to improve and broaden access to mental healthcare. When designing chatbots for mental healthcare, there are further considerations, such as managing risk and ethical considerations. Furthermore, usability and the design of conversational flow are important factors to consider when developing chatbots for any domain. This paper outlines best practices and experiences extrapolated from developing the iHelpr chatbot.

Assessing the Usability of a Chatbot for Mental Health Care

“…Usability questionnaires are discussed, and adapted to create a usability test to assess the iHelpr chatbot. This paper is a continuation of previous work completed in the area of chatbots for mental health care [5][6][7].…”

“…In previous works [5][6][7], Inspire Workplaces developed a chatbot, iHelpr, in partnership with Ulster University through a Knowledge Transfer Partnership. Inspire Workplaces provide programmes and wellbeing solutions for private and public sector organisations, and educational institutions across the island of Ireland.…”

Usability testing of a healthcare chatbot: Can we use conventional methods to assess conversational user interfaces?

“…In response to growing waiting lists and difficulties in accessing mental health services, Cameron et al (2018) developed iHelpr, a self-help mental health chatbot. It is suggested that conversational interfaces may soon replace web pages and smartphone apps as the preferred means of conducting online tasks [8]. Chatbots are suggested to be of use in the area of mental health because they provide instant access to help and support and increased efficiency [6].…”

Conversational Agents for Mental Health and Wellbeing

“…Mulvenna et al [102] present a manifesto with 12 principles as a starting point for ethical by design development of chatbots for mental health, which they have used to develop the iHelpr system [103]. These include among others empathy for users, providing informed decisions, respect to choose ways to be engaged, privacy and security, equitable access and complementary viewpoints, challenge possible biased incorporated into the system, support through lifespan and progression policy, planning for failure, transparency and reporting.…”