Making the case for audience design in conversational AI: Rapport expectations and language ideologies in a task-oriented chatbot
This work addresses improving chatbot usability and equity for users in task-oriented contexts, but it is incremental as it builds on existing sociolinguistic theories.
The paper tackles the problem of designing conversational AI to meet users' rapport expectations and language ideologies, using simulated interactions and user feedback to argue for audience design that ensures equitable access to services.
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.