This paper aims to discuss some relevant evaluation criteria and suggestions for the improvement of text-based chatbots for tourism-specific German as Foreign Language classes in an academic setting. After outlining some findings of the research on chatbot-based language learning and some requirements for future professionals in tourism, the paper offers an analysis of two chatbots (i. e. Duolingo Bots and Lufthansa BestPrice) considering their use for touristic German learning at university. The selected findings show that it is still problematic for chatbots to switch the chat partners’ role and to give high-quality feedback on users’ input.

Kriterien und Vorschläge zur Evaluation textbasierter Chatbots für die touristische Sprachbildung am Beispiel von Lufthansa BestPrice und Duolingo Bots

Mazzilli, Francesca
2019

Abstract

This paper aims to discuss some relevant evaluation criteria and suggestions for the improvement of text-based chatbots for tourism-specific German as Foreign Language classes in an academic setting. After outlining some findings of the research on chatbot-based language learning and some requirements for future professionals in tourism, the paper offers an analysis of two chatbots (i. e. Duolingo Bots and Lufthansa BestPrice) considering their use for touristic German learning at university. The selected findings show that it is still problematic for chatbots to switch the chat partners’ role and to give high-quality feedback on users’ input.
Ziel dieses Beitrags sind die Diskussion von fremdsprachendidaktisch relevanten Evaluationskriterien und die Formulierung von Verbesserungsvorschlägen bezüglich textbasierter Chatbots für den universitären tourismusbezogenen DaF-Unterricht. Hierzu wird nach einer Einführung in die Ergebnisse der Forschung zum chatbotgestützten Fremdsprachenunterricht sowie in die Anforderungen an das angestrebte Berufsprofil von Tourismusbeschäftigten das Angebot der Chatbots Duolingo Bots und Lufthansa BestPrice im Hinblick auf die berufsvorbereitende Sprachlehrpraxis analysiert. Ausgewählte Ergebnisse zeigen, dass der Rollenwechsel der Chat-Partner sowie die Qualität der Rückmeldung der untersuchten Chatbots immer noch problematisch sind.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11586/256631
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact