Making the case for audience design in conversational AI: Rapport expectations and language ideologies in a task-oriented chatbot

TL;DR

This paper emphasizes the importance of understanding users' language ideologies and rapport expectations to improve audience design in conversational AI, ensuring more equitable and effective interactions.

Contribution

It introduces a framework combining sociolinguistic rapport management with user-centered analysis to inform audience design in task-oriented chatbots.

Findings

User interactions reveal diverse language ideologies affecting rapport

Qualitative data highlight the importance of tailored interaction patterns

Audience design can enhance chatbot accessibility and user satisfaction

Abstract

Chatbots are more and more prevalent in commercial and science contexts. They help customers complain about a product or service or support them to find the best travel deals. Other bots provide mental health support or help book medical appointments. This paper argues that insights into users' language ideologies and their rapport expectations can be used to inform the audience design of the bot's language and interaction patterns and ensure equitable access to the services provided by bots. The argument is underpinned by three kinds of data: simulated user interactions with a chatbot facilitating health appointment bookings, users' introspective comments on their interactions and users' qualitative survey comments post engagement with the booking bot. In closing, I will define audience design for conversational AI and discuss how user-centred analyses of chatbot interactions and sociolinguistically informed theoretical approaches, such as rapport management, can be used to support audience design.