Asbjørn Følstad
Conversational Breakdown in a Customer Service Chatbot: Impact of Task Order and Criticality on User Trust and Emotion
Følstad, Asbjørn; Law, Effie L-C.; van As, Nena
Abstract
While chatbots are increasingly used for customer service, there is a knowledge gap concerning the impact of Conversational Breakdown in such chatbot interactions. In a 2 × 4 factorial design online experiment, we studied how Conversational Breakdown impacts user emotion and trust in a chatbot for customer service, given variations in task criticality and breakdown task order. Here, 257 participants were randomly assigned to complete high-or low-criticality tasks with a prototype chatbot for customer service, experiencing Conversational Breakdown for the first, second, third or none of their tasks. The task set was decided from a 63-participant pre-study. We found significant impact of Conversational Breakdown, including a marked order effect on overall trust, as well as a bounce-back effect on task-specific trust and emotion after subsequent successful task completion. We found no post-interaction effect of Task Criticality. Based on our findings, we discuss theoretical and practical implications and suggest future research.
Citation
Følstad, A., Law, E. L.-C., & van As, N. (2024). Conversational Breakdown in a Customer Service Chatbot: Impact of Task Order and Criticality on User Trust and Emotion. ACM Transactions on Computer-Human Interaction, 31(5), 1-52. https://doi.org/10.1145/3690383
Journal Article Type | Article |
---|---|
Acceptance Date | Jul 31, 2024 |
Online Publication Date | Sep 3, 2024 |
Publication Date | 2024-10 |
Deposit Date | Sep 26, 2024 |
Publicly Available Date | Sep 26, 2024 |
Journal | ACM Transactions on Computer-Human Interaction |
Print ISSN | 1073-0516 |
Electronic ISSN | 1557-7325 |
Publisher | Association for Computing Machinery (ACM) |
Peer Reviewed | Peer Reviewed |
Volume | 31 |
Issue | 5 |
Article Number | 66 |
Pages | 1-52 |
DOI | https://doi.org/10.1145/3690383 |
Keywords | CCS Concepts:; Human-centred computing; Human-computer interaction (HCI); Interaction paradigms; Natural language interfaces; Additional Key Words and Phrases: Conversational agent, Conversational Breakdown, Task Criticality, Trust, AQ3 |
Public URL | https://durham-repository.worktribe.com/output/2876950 |
Files
Accepted Journal Article
(1.1 Mb)
PDF
Published Journal Article
(29 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
You might also like
Trustworthy Autonomous Systems Through Verifiability
(2023)
Journal Article
Building a three-level multimodal emotion recognition framework
(2022)
Journal Article
Future directions for chatbot research: an interdisciplinary research agenda
(2021)
Journal Article
How easy is it to eXtend Reality? A Usability Study of Authoring Toolkits
(2022)
Book Chapter
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2025
Advanced Search