Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

User Preference and Categories for Error Responses in Conversational User Interfaces

Paper presented at 2nd Conference on Conversational User Interfaces, CUI 2020, July 22-24, 2020, Bilbao, Spain
Benutzereinstellungen und Kategorien für Fehlerantworten in Konversationsbenutzeroberflächen
: Yuan, Sihan; Brüggemeier, Birgit; Hillmann, Stefan; Michael, Thilo

Preprint urn:nbn:de:0011-n-5932714 (314 KByte PDF)
MD5 Fingerprint: 5804585980ec557d7b1adbeee03e520b
Erstellt am: 25.6.2020

Torres, M.I. ; Association for Computing Machinery -ACM-:
2nd Conference on Conversational User Interfaces 2020. Proceedings : Bilbao, Spain, July, 2020
New York: ACM, 2020
ISBN: 978-1-4503-7544-3
Art. 5, 8 S.
Conference on Conversational User Interfaces (CUI) <2, 2020, Online>
Bundesministerium fur Wirtschaft und Energie BMWi (Deutschland)
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IIS ()
conversational user interface; error response; user experience

Error messages are frequent in interactions with Conversational User Interfaces (CUI). Smart speakers respond to about every third user request with an error message. Errors can heavily affect user experience (UX) in interaction with CUI. However, there is limited research on how error responses should be formulated. In this paper, we present a system to study how people classify different categories (acknowledgement of user sentiment, acknowledgement of error and apology) of error messages, and evaluate peoples preference of error responses with clear categories. The results indicate that if an error response has only one element (i.e. neutral acknowledgement of error, apology or sentiment), responses that acknowledge errors neutrally are preferred by participants. Moreover, we find that when interviewed, participants like error messages to include an apology, an explanation of what went wrong, and a suggestion how to fix the problem in addition to a neutral acknowledgement of an error. Our study has two main contributions: (1) our results inform about the design of error messages and (2) we present a framework for error response categorization and validation.