Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding knowledge in a suitable format. Recent advances in language learning models with zero-shot learning capabilities, such as ChatGPT, suggest a new possibility for developing educational chatbots using a prompt-based approach. We present a case study with a simple system that enables mixed-turn interactions and discuss the insights and preliminary guidelines obtained from initial tests. We examine ChatGPT's ability to pursue natural educational conversations, adapt the educational activity to users' characteristics, such as culture, age, and level of education, and its ability to use diverse educational strategies and conversational styles. Although the results are encouraging, challenges are posed by the highly structured form of responses by ChatGPT, as well as their variability, which can lead to an unexpected switch of the chatbot's role from a teacher to a therapist. We provide some initial guidelines to address these issues and to facilitate the development of effective educational chatbots.
Koyuturk, C., Yavari, M., Theophilou, E., Bursic, S., Donabauer, G., Telari, A., et al. (2023). Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy. In 31st International Conference on Computers in Education, ICCE 2023 - Proceedings (pp.150-152). Asia-Pacific Society for Computers in Education.
Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy
Koyuturk C.
Primo
;Yavari M.Secondo
;Bursic S.;Donabauer G.;Telari A.;Gabbiadini A.;Ognibene D.
Ultimo
2023
Abstract
Educational chatbots come with a promise of interactive and personalized learning experiences, yet their development has been limited by the restricted free interaction capabilities of available platforms and the difficulty of encoding knowledge in a suitable format. Recent advances in language learning models with zero-shot learning capabilities, such as ChatGPT, suggest a new possibility for developing educational chatbots using a prompt-based approach. We present a case study with a simple system that enables mixed-turn interactions and discuss the insights and preliminary guidelines obtained from initial tests. We examine ChatGPT's ability to pursue natural educational conversations, adapt the educational activity to users' characteristics, such as culture, age, and level of education, and its ability to use diverse educational strategies and conversational styles. Although the results are encouraging, challenges are posed by the highly structured form of responses by ChatGPT, as well as their variability, which can lead to an unexpected switch of the chatbot's role from a teacher to a therapist. We provide some initial guidelines to address these issues and to facilitate the development of effective educational chatbots.File | Dimensione | Formato | |
---|---|---|---|
ICCE 2023-VoR.pdf
Solo gestori archivio
Descrizione: Intervento a convegno - Conference proceedings
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Tutti i diritti riservati
Dimensione
63.37 MB
Formato
Adobe PDF
|
63.37 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Koyuturk-2023-ICCE 2023-VoR.pdf
Solo gestori archivio
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Tutti i diritti riservati
Dimensione
1.23 MB
Formato
Adobe PDF
|
1.23 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.