Adapting a Virtual Advisor’s Verbal Conversation Based on Predicted User Preferences: A Study of Neutral, Empathic and Tailored Dialogue

Hedieh Ranjbartabar,Samuel Mascarenhas,Cat Kutay,Deborah Richards,Ayse Aysin Bilgin

doi:10.3390/mti4030055

Abstract

Virtual agents that improve the lives of humans need to be more than user-aware and adaptive to the user’s current state and behavior. Additionally, they need to apply expertise gained from experience that drives their adaptive behavior based on deep understanding of the user’s features (such as gender, culture, personality, and psychological state). Our work has involved extension of FAtiMA (Fearnot AffecTive Mind Architecture) with the addition of an Adaptive Engine to the FAtiMA cognitive agent architecture. We use machine learning to acquire the agent’s expertise by capturing a collection of user profiles into a user model and development of agent expertise based on the user model. In this paper, we describe a study to evaluate the Adaptive Engine, which compares the benefit (i.e., reduced stress, increased rapport) of tailoring dialogue to the specific user (Adaptive group) with dialogues that are either empathic (Empathic group) or neutral (Neutral group). Results showed a significant reduction in stress in the empathic and neutral groups, but not the adaptive group. Analyses of rule accuracy, participants’ dialogue preferences, and individual differences reveal that the three groups had different needs for empathic dialogue and highlight the importance and challenges of getting the tailoring right.

Highlights

There are many potential applications of intelligent virtual agents, virtual humans with the ability to interact intelligently with humans
We have extended FAtiMA with an Adaptive Engine comprised of a collection or repository of User Models, one for each user, and an Agent Expertise module that represents what the agent has learnt by interacting with a range of users in the past
To evaluate the dialogue provided by adaptive Sarah, we presented 20 empathic sentences and asked the participants to specify if they found it empathic, helpful and/or stupid

Summary

Introduction

There are many potential applications of intelligent virtual agents, virtual humans with the ability to interact intelligently with humans. They could perform social roles, such as a virtual advisor. We consider the role of empathy and approaches to empathic agents, followed by a review of ways in which agents may adapt to the user. Empathic agents are designed to detect the user’s emotion and respond in an emotionally intelligent way. Empathy can involve cognitive or affective attributes. The former involves reasoning to understand and demonstrate this understanding of the user. Affective attributes involve physiological responses and rapid expression change responding to someone else’s display of emotions, such as mimicry.

Objectives

Methods

Findings

Conclusion