Mirroring to Build Trust in Digital Assistants
This addresses the challenge of user trust in conversational AI, though it is incremental as it builds on existing work in personalization and human-computer interaction.
The researchers tackled the problem of building trust in digital assistants by matching the assistant's conversational style to the user's, finding that users preferred and trusted assistants that mirrored their style. They developed models that reliably predict a user's preferred conversational style based on personality attributes and feedback.
We describe experiments towards building a conversational digital assistant that considers the preferred conversational style of the user. In particular, these experiments are designed to measure whether users prefer and trust an assistant whose conversational style matches their own. To this end we conducted a user study where subjects interacted with a digital assistant that responded in a way that either matched their conversational style, or did not. Using self-reported personality attributes and subjects' feedback on the interactions, we built models that can reliably predict a user's preferred conversational style.