Using LLMs to adapt serious games with educators in the loop
Using LLMs to adapt serious games with educators in the loop
Recently, the advancement of generative AI has brought about the opportunity to adapt and personalize learning material to individual students with little effort. This paper explores the application of large language models, such as ChatGPT, to help educators adapt educational serious games at runtime. To incorporate adaptation into serious games in a systematic way, we employ the MAPE-K loop framework. A key focus is the inclusion of educators in the adaptation process, who ensure that AI-driven changes align with educational goals. We thus propose an architecture that integrates player/learner data, game logic, and AI-generated adaptations, monitored and approved by educators via a dedicated browser-based dashboard, in a human-in-the-loop fashion. We show how we integrated this architecture into Untitled Bee Game, an existing educational serious game for eco-sustainability.
adaptation, education, mape-k loop, serious games, sustainability
68-77
Bonetti, Federico
7fb0a465-2800-40c0-88ca-122abecde104
Bucchiarone, Antonio
725ea4e4-cc11-4b58-8aea-11e8ee8a9f26
Wanick, Vanissa
d2941cae-269e-4672-b448-8cb93e22e89e
Bonetti, Federico
7fb0a465-2800-40c0-88ca-122abecde104
Bucchiarone, Antonio
725ea4e4-cc11-4b58-8aea-11e8ee8a9f26
Wanick, Vanissa
d2941cae-269e-4672-b448-8cb93e22e89e
Bonetti, Federico, Bucchiarone, Antonio and Wanick, Vanissa
(2024)
Using LLMs to adapt serious games with educators in the loop.
Schönbohm, Avo, Bellotti, Francesco, Bucchiarone, Antonio, de Rosa, Francesca, Ninaus, Manuel, Wang, Alf, Wanick, Vanissa and Dondio, Pierpaolo
(eds.)
In Games and Learning Alliance - 13th International Conference, GALA 2024, Proceedings.
vol. 15348 LNCS,
Springer Cham.
.
(doi:10.1007/978-3-031-78269-5_7).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Recently, the advancement of generative AI has brought about the opportunity to adapt and personalize learning material to individual students with little effort. This paper explores the application of large language models, such as ChatGPT, to help educators adapt educational serious games at runtime. To incorporate adaptation into serious games in a systematic way, we employ the MAPE-K loop framework. A key focus is the inclusion of educators in the adaptation process, who ensure that AI-driven changes align with educational goals. We thus propose an architecture that integrates player/learner data, game logic, and AI-generated adaptations, monitored and approved by educators via a dedicated browser-based dashboard, in a human-in-the-loop fashion. We show how we integrated this architecture into Untitled Bee Game, an existing educational serious game for eco-sustainability.
Text
Accepted Manuscript
- Accepted Manuscript
Restricted to Repository staff only until 18 December 2025.
Request a copy
More information
e-pub ahead of print date: 18 December 2024
Venue - Dates:
13th International Conference on Games and Learning Alliance, GALA 2024, , Berlin, Germany, 2024-11-20 - 2024-11-22
Keywords:
adaptation, education, mape-k loop, serious games, sustainability
Identifiers
Local EPrints ID: 498436
URI: http://eprints.soton.ac.uk/id/eprint/498436
ISSN: 0302-9743
PURE UUID: 415792c0-f658-4fcb-a9d8-e8b4445d8f15
Catalogue record
Date deposited: 18 Feb 2025 17:45
Last modified: 18 Sep 2025 01:53
Export record
Altmetrics
Contributors
Author:
Federico Bonetti
Author:
Antonio Bucchiarone
Editor:
Avo Schönbohm
Editor:
Francesco Bellotti
Editor:
Antonio Bucchiarone
Editor:
Francesca de Rosa
Editor:
Manuel Ninaus
Editor:
Alf Wang
Editor:
Vanissa Wanick
Editor:
Pierpaolo Dondio
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
