Troubleshooting Conversations: Exploring Chatbot Repair Strategies

Chatbots are increasingly used in various domains, but since misunderstandings nonetheless occur, robust strategies are required to handle these misunderstandings and ensure smooth interactions. The evaluation of a faulty chatbot can depend on various factors, for example the task domain or the characteristics of the user. This short paper provides an overview of three different repair strategies for chatbots, taking into account the users’ affinity for technology. The conducted experimental psychological study investigates these three strategies, i.e. the requests for rephrasing, offering suggestions of what might be meant, and politeness to handle conversational errors. Results indicate that providing suggestions has a positive influence on the perceived Accuracy and Likability of the chatbot. Additionally, it seems that the combination of repair strategies should also be considered. Overall, this research contributes to a deeper understanding of ways to recover from a misunderstanding and provides guidelines for the implementation of different repair strategies for chatbot interaction.

Authors

Institutions

Publication Details

Published
2024-08-26
DOI
https://doi.org/10.1145/3670653.3677496
Primary Topic
AI in Service Interactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Troubleshooting Conversations: Exploring Chatbot Repair Strategies

Kinga Schumacher, Eva Schwaetzer, Marilena Wilhelm, Tabea Otten et al.
AI in Service Interactions
article

Troubleshooting Conversations: Exploring Chatbot Repair Strategies

Kinga Schumacher, Eva Schwaetzer, Marilena Wilhelm, Tabea Otten, Theresa Zobel
article en

Abstract

Chatbots are increasingly used in various domains, but since misunderstandings nonetheless occur, robust strategies are required to handle these misunderstandings and ensure smooth interactions. The evaluation of a faulty chatbot can depend on various factors, for example the task domain or the characteristics of the user. This short paper provides an overview of three different repair strategies for chatbots, taking into account the users’ affinity for technology. The conducted experimental psychological study investigates these three strategies, i.e. the requests for rephrasing, offering suggestions of what might be meant, and politeness to handle conversational errors. Results indicate that providing suggestions has a positive influence on the perceived Accuracy and Likability of the chatbot. Additionally, it seems that the combination of repair strategies should also be considered. Overall, this research contributes to a deeper understanding of ways to recover from a misunderstanding and provides guidelines for the implementation of different repair strategies for chatbot interaction.

Hasso Plattner Institute (DE), German Research Centre for Artificial Intelligence (DE)
Openalex Percentile: Top 88%
AI in Service Interactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.