Logo des Repositoriums
 
Konferenzbeitrag

Troubleshooting Conversations: Exploring Chatbot Repair Strategies

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2024

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Association for Computing Machinery

Zusammenfassung

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.

Beschreibung

Wilhelm, Marilena; Schwaetzer, Eva; Otten, Tabea; Zobel, Theresa Elfriede Isa; Schumacher, Kinga (2024): Troubleshooting Conversations: Exploring Chatbot Repair Strategies. Proceedings of Mensch und Computer 2024. DOI: 10.1145/3670653.3677496. Association for Computing Machinery. pp. 386–391. Karlsruhe, Germany

Zitierform

Tags