Enhancing User Forgiveness in AI Service Failures: A Feature-Attribution Explanation Framework for Chatbots

DOI

10.2991/978-94-6239-733-0_40How to use a DOI?

Keywords

Algorithmic Interpretability; Human-computer Interaction; Users’ Willingness to Forgive; Chatbot Design

Abstract

Obtaining user forgiveness after an AI service failure is crucial for sustaining human–machine trust. This study, from the perspective of explainable AI, investigates the impact mechanism of providing post-hoc algorithmic explanations in service recovery on users’ forgiveness intention. We designed and implemented two AI customer service dialog agents with varying levels of explanation: one offering transparent explanations based on user data and feature weights, and the other providing only vague, formulaic responses. Grounded in Expectancy Violations Theory, two online human–AI interaction experiments (N = 393) revealed that algorithmic explanations effectively enhance users’ perceived control, thereby increasing their willingness to forgive. More importantly, users’ prior expectations moderate this mediating effect: for users with low expectations, the boost in perceived control from explanations exerts a stronger promoting effect on forgiveness intention. This study provides empirical evidence and design insights for developing explaining AI systems in service failure scenarios.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yihan Liao
PY  - 2026
DA  - 2026/07/17
TI  - Enhancing User Forgiveness in AI Service Failures: A Feature-Attribution Explanation Framework for Chatbots
BT  - Proceedings of the 6th International Conference on Internet, Education and Information Technology (IEIT 2026)
PB  - Atlantis Press
SP  - 385
EP  - 394
SN  - 2667-128X
UR  - https://doi.org/10.2991/978-94-6239-733-0_40
DO  - 10.2991/978-94-6239-733-0_40
ID  - Liao2026
ER  -