First impressions count!: The role of the human's emotional state on rapport established with an empathic versus neutral virtual therapist

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Intelligent virtual agents are being endowed with empathic behaviours to perform roles such as virtual therapists. Studies often evaluate the level of rapport established, but do not measure the therapeutic benefit and the relative advantage of empathic versus neutral behaviours. We have created two virtual (empathic/neutral) therapists. Our experiment with 63 participants consisted of one within-subjects (empathic/neutral) and one between-subjects (order) factors. Regardless of the virtual therapist used, improvements in baseline emotion were reported after the first interaction (time one) and further improvement after the second interaction (time two). Our study reveals that if the human initially expresses strong emotional feeling for a problem they are facing, rapport will be higher for the empathic therapist and the level of rapport established at the first meeting will persist regardless of whether the second encounter used empathic or neutral dialogue. Conversely, participants experiencing low emotional feeling reported greater rapport with the neutral therapist, and that level of rapport persisted in the second encounter with the alternative therapist. This study shows that an empathic agent will not necessarily build more rapport or deliver better emotional outcomes than a neutral agent. Further studies are needed to determine when tailoring and complex behaviours are justified.

LanguageEnglish
JournalIEEE Transactions on Affective Computing
DOIs
Publication statusAccepted/In press - 14 Feb 2019

Fingerprint

Intelligent virtual agents
Experiments

Keywords

  • Empathic Agents
  • Intelligent Virtual Agents
  • Virtual Therapist

Cite this

@article{8aa13aba3bee443cb97007b47ff564a6,
title = "First impressions count!: The role of the human's emotional state on rapport established with an empathic versus neutral virtual therapist",
abstract = "Intelligent virtual agents are being endowed with empathic behaviours to perform roles such as virtual therapists. Studies often evaluate the level of rapport established, but do not measure the therapeutic benefit and the relative advantage of empathic versus neutral behaviours. We have created two virtual (empathic/neutral) therapists. Our experiment with 63 participants consisted of one within-subjects (empathic/neutral) and one between-subjects (order) factors. Regardless of the virtual therapist used, improvements in baseline emotion were reported after the first interaction (time one) and further improvement after the second interaction (time two). Our study reveals that if the human initially expresses strong emotional feeling for a problem they are facing, rapport will be higher for the empathic therapist and the level of rapport established at the first meeting will persist regardless of whether the second encounter used empathic or neutral dialogue. Conversely, participants experiencing low emotional feeling reported greater rapport with the neutral therapist, and that level of rapport persisted in the second encounter with the alternative therapist. This study shows that an empathic agent will not necessarily build more rapport or deliver better emotional outcomes than a neutral agent. Further studies are needed to determine when tailoring and complex behaviours are justified.",
keywords = "Empathic Agents, Intelligent Virtual Agents, Virtual Therapist",
author = "Hedieh Ranjbartabar and Deborah Richards and Ayse Bilgin and Cat Kutay",
year = "2019",
month = "2",
day = "14",
doi = "10.1109/TAFFC.2019.2899305",
language = "English",
journal = "IEEE Transactions on Affective Computing",
issn = "1949-3045",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - First impressions count!

T2 - IEEE Transactions on Affective Computing

AU - Ranjbartabar, Hedieh

AU - Richards, Deborah

AU - Bilgin, Ayse

AU - Kutay, Cat

PY - 2019/2/14

Y1 - 2019/2/14

N2 - Intelligent virtual agents are being endowed with empathic behaviours to perform roles such as virtual therapists. Studies often evaluate the level of rapport established, but do not measure the therapeutic benefit and the relative advantage of empathic versus neutral behaviours. We have created two virtual (empathic/neutral) therapists. Our experiment with 63 participants consisted of one within-subjects (empathic/neutral) and one between-subjects (order) factors. Regardless of the virtual therapist used, improvements in baseline emotion were reported after the first interaction (time one) and further improvement after the second interaction (time two). Our study reveals that if the human initially expresses strong emotional feeling for a problem they are facing, rapport will be higher for the empathic therapist and the level of rapport established at the first meeting will persist regardless of whether the second encounter used empathic or neutral dialogue. Conversely, participants experiencing low emotional feeling reported greater rapport with the neutral therapist, and that level of rapport persisted in the second encounter with the alternative therapist. This study shows that an empathic agent will not necessarily build more rapport or deliver better emotional outcomes than a neutral agent. Further studies are needed to determine when tailoring and complex behaviours are justified.

AB - Intelligent virtual agents are being endowed with empathic behaviours to perform roles such as virtual therapists. Studies often evaluate the level of rapport established, but do not measure the therapeutic benefit and the relative advantage of empathic versus neutral behaviours. We have created two virtual (empathic/neutral) therapists. Our experiment with 63 participants consisted of one within-subjects (empathic/neutral) and one between-subjects (order) factors. Regardless of the virtual therapist used, improvements in baseline emotion were reported after the first interaction (time one) and further improvement after the second interaction (time two). Our study reveals that if the human initially expresses strong emotional feeling for a problem they are facing, rapport will be higher for the empathic therapist and the level of rapport established at the first meeting will persist regardless of whether the second encounter used empathic or neutral dialogue. Conversely, participants experiencing low emotional feeling reported greater rapport with the neutral therapist, and that level of rapport persisted in the second encounter with the alternative therapist. This study shows that an empathic agent will not necessarily build more rapport or deliver better emotional outcomes than a neutral agent. Further studies are needed to determine when tailoring and complex behaviours are justified.

KW - Empathic Agents

KW - Intelligent Virtual Agents

KW - Virtual Therapist

UR - http://www.scopus.com/inward/record.url?scp=85061527249&partnerID=8YFLogxK

U2 - 10.1109/TAFFC.2019.2899305

DO - 10.1109/TAFFC.2019.2899305

M3 - Article

JO - IEEE Transactions on Affective Computing

JF - IEEE Transactions on Affective Computing

SN - 1949-3045

ER -