Abstract
Inspired by the role of therapist-patient relationship in fostering behaviour change, agent-human relationship has been an active research area. This trusted relationship could be a result of the agent’s behavioural cues or the content it delivers that shows its knowledge. However, the impact of the resulting relationship using the various strategies on behaviour change is understudied. In this paper, we investigate the role of two strategies (empathic and social dialogue and explanation) in building agent-user rapport and whether the level of behaviour change intentions are due to the use of empathy or to trusting the agent’s understanding and recommendations through explanation. Hence, we designed two versions of a virtual advisor, empathic and neutral, to reduce study stress among university students and measured students’ rapport levels and intentions to change their behaviour. Some recommended behaviours had explanations based on the user’s beliefs. Our results showed that the agent could build a trusting relationship with the user with the help of the explanation regardless of the level of rapport. The results further showed that nearly all of the recommendations provided by the agent highly significantly increased the intention of the user to change their behavior related to these recommendations. However, we also found that it is important for the agent to obtain and reason about the user’s intentions concerning the specific behaviour before recommending a certain behavior change.
Original language | English |
---|---|
Pages (from-to) | 189-199 |
Number of pages | 11 |
Journal | Journal on Multimodal User Interfaces |
Volume | 15 |
Issue number | 2 |
Early online date | 18 Jan 2021 |
DOIs | |
Publication status | Published - Jun 2021 |
Keywords
- Behaviour change
- Explainable AI
- Intelligent virtual agents
- Rapport
- Working alliance