ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery

Emiliana Murgia; Zahra Abbasiantaeb; Mohammad Aliannejadi; Theo Huibers; Monica Landoni; Maria Soledad Pera

doi:10.1145/3563359.3597399

ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery

Emiliana Murgia, Zahra Abbasiantaeb, Mohammad Aliannejadi, Theo Huibers, Monica Landoni, Maria Soledad Pera

Web Information Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Citation (Scopus)

Abstract

The influence of ChatGPT and similar models on education is being increasingly discussed. With the current level of enthusiasm among users, ChatGPT is envisioned as having great potential. As generative models are unpredictable in terms of producing biased, harmful, and unsafe content, we argue that they should be comprehensively tested for more vulnerable groups, such as children, to understand what role they can play and what training and supervision are necessary. Here, we present the results of a preliminary exploration aiming to understand whether ChatGPT can adapt to support children in completing information discovery tasks in the education context. We analyze ChatGPT responses to search prompts related to the 4th grade classroom curriculum using a variety of lenses (e.g., readability and language) to identify open challenges and limitations that must be addressed by interdisciplinary communities.

Original language	English
Title of host publication	UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization
Publisher	Association for Computing Machinery (ACM)
Pages	22-27
Number of pages	6
ISBN (Electronic)	9781450398916
DOIs	https://doi.org/10.1145/3563359.3597399
Publication status	Published - 2023
Event	31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2023 - Limassol, Cyprus Duration: 26 Jun 2023 → 30 Jun 2023

Publication series

Name	UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization

Conference

Conference	31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2023
Country/Territory	Cyprus
City	Limassol
Period	26/06/23 → 30/06/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Access to Document

10.1145/3563359.3597399

Cite this

Murgia, E., Abbasiantaeb, Z., Aliannejadi, M., Huibers, T., Landoni, M., & Pera, M. S. (2023). ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery. In UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization (pp. 22-27). (UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization). Association for Computing Machinery (ACM). https://doi.org/10.1145/3563359.3597399

Murgia, Emiliana ; Abbasiantaeb, Zahra ; Aliannejadi, Mohammad et al. / ChatGPT in the Classroom : A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery. UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery (ACM), 2023. pp. 22-27 (UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization).

@inproceedings{ff1b0a1d667b4f41a5fa1d8a1c297b37,

title = "ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery",

abstract = "The influence of ChatGPT and similar models on education is being increasingly discussed. With the current level of enthusiasm among users, ChatGPT is envisioned as having great potential. As generative models are unpredictable in terms of producing biased, harmful, and unsafe content, we argue that they should be comprehensively tested for more vulnerable groups, such as children, to understand what role they can play and what training and supervision are necessary. Here, we present the results of a preliminary exploration aiming to understand whether ChatGPT can adapt to support children in completing information discovery tasks in the education context. We analyze ChatGPT responses to search prompts related to the 4th grade classroom curriculum using a variety of lenses (e.g., readability and language) to identify open challenges and limitations that must be addressed by interdisciplinary communities. ",

author = "Emiliana Murgia and Zahra Abbasiantaeb and Mohammad Aliannejadi and Theo Huibers and Monica Landoni and Pera, {Maria Soledad}",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2023 ; Conference date: 26-06-2023 Through 30-06-2023",

year = "2023",

doi = "10.1145/3563359.3597399",

language = "English",

series = "UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization",

publisher = "Association for Computing Machinery (ACM)",

pages = "22--27",

booktitle = "UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization",

address = "United States",

}

Murgia, E, Abbasiantaeb, Z, Aliannejadi, M, Huibers, T, Landoni, M & Pera, MS 2023, ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery. in UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization. UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, Association for Computing Machinery (ACM), pp. 22-27, 31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2023, Limassol, Cyprus, 26/06/23. https://doi.org/10.1145/3563359.3597399

ChatGPT in the Classroom : A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery. / Murgia, Emiliana; Abbasiantaeb, Zahra; Aliannejadi, Mohammad et al.

UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery (ACM), 2023. p. 22-27 (UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - ChatGPT in the Classroom

T2 - 31st ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2023

AU - Murgia, Emiliana

AU - Abbasiantaeb, Zahra

AU - Aliannejadi, Mohammad

AU - Huibers, Theo

AU - Landoni, Monica

AU - Pera, Maria Soledad

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - The influence of ChatGPT and similar models on education is being increasingly discussed. With the current level of enthusiasm among users, ChatGPT is envisioned as having great potential. As generative models are unpredictable in terms of producing biased, harmful, and unsafe content, we argue that they should be comprehensively tested for more vulnerable groups, such as children, to understand what role they can play and what training and supervision are necessary. Here, we present the results of a preliminary exploration aiming to understand whether ChatGPT can adapt to support children in completing information discovery tasks in the education context. We analyze ChatGPT responses to search prompts related to the 4th grade classroom curriculum using a variety of lenses (e.g., readability and language) to identify open challenges and limitations that must be addressed by interdisciplinary communities.

AB - The influence of ChatGPT and similar models on education is being increasingly discussed. With the current level of enthusiasm among users, ChatGPT is envisioned as having great potential. As generative models are unpredictable in terms of producing biased, harmful, and unsafe content, we argue that they should be comprehensively tested for more vulnerable groups, such as children, to understand what role they can play and what training and supervision are necessary. Here, we present the results of a preliminary exploration aiming to understand whether ChatGPT can adapt to support children in completing information discovery tasks in the education context. We analyze ChatGPT responses to search prompts related to the 4th grade classroom curriculum using a variety of lenses (e.g., readability and language) to identify open challenges and limitations that must be addressed by interdisciplinary communities.

UR - http://www.scopus.com/inward/record.url?scp=85163725878&partnerID=8YFLogxK

U2 - 10.1145/3563359.3597399

DO - 10.1145/3563359.3597399

M3 - Conference contribution

AN - SCOPUS:85163725878

T3 - UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization

SP - 22

EP - 27

BT - UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization

PB - Association for Computing Machinery (ACM)

Y2 - 26 June 2023 through 30 June 2023

ER -

Murgia E, Abbasiantaeb Z, Aliannejadi M, Huibers T, Landoni M, Pera MS. ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery. In UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery (ACM). 2023. p. 22-27. (UMAP 2023 - Adjunct Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization). doi: 10.1145/3563359.3597399

ChatGPT in the Classroom: A Preliminary Exploration on the Feasibility of Adapting ChatGPT to Support Children's Information Discovery

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Embargoed Document

Fingerprint

Cite this