AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions

Wilkinson Daniel Wong GONZALES; Daniel Jiandong SHEN; Aihua YAN; Nina XIE; Maria Leonora FRANCISCO; Paulina Pui Yun WONG

doi:10.1007/978-981-96-4952-5_4

AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions

Wilkinson Daniel Wong GONZALES^*, Daniel Jiandong SHEN, Aihua YAN, Nina XIE, Maria Leonora FRANCISCO, Paulina Pui Yun WONG

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

Abstract

The purpose of this study was to evaluate the effectiveness and relevance of AI-powered non-player characters (NPCs) in educational settings within the metaverse platform Classlet, particularly within the domain of applied social sciences. Integrating Speech Act Theory, Prospect Theory, and the Recognition-Primed Decision Model into AI prompt templates enhanced interactions and positively impacted student engagement. The AI NPCs achieved a performance ratio of 128%, providing contextually relevant responses effectively maintained by the prompt templates. A survey on students’ perceptions of the AI and VR integration revealed positive user perceptions, with strong correlations between enjoyment, perceived usefulness, and intent to use. Correlational analysis showed a strong fit (R2 = 0.816) for user intent, which had a mean of 74%. U-tests also indicated that female and non-VR users encountered more technical difficulties. Overall, the results suggest new ways of using AI and VR to promote learning engagement and interactions within applied social sciences.

Original language	English
Title of host publication	Innovating Education with AI : AETS 2024
Editors	Eric C. K. CHENG
Publisher	Springer Singapore
Chapter	4
Pages	53-74
Number of pages	22
ISBN (Electronic)	9789819649525
ISBN (Print)	9789819649518
DOIs	https://doi.org/10.1007/978-981-96-4952-5_4
Publication status	Published - 16 Apr 2025

Publication series

Name	Lecture Notes in Educational Technology
Publisher	Springer
Volume	Part F312
ISSN (Print)	2196-4963
ISSN (Electronic)	2196-4971

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Funding

Lingnan University, Hong Kong (Teaching Development Grant, Project Code: 102716; Fund for Innovative Technology-in-Education (FITE) by the University Grants Committee (Project Code: 120042).

Keywords

Adaptive Learning Environments
AI Educational Agents
AI in Education

Access to Document

10.1007/978-981-96-4952-5_4

https://link.springer.com/10.1007/978-981-96-4952-5_4

Cite this

GONZALES, W. D. W., SHEN, D. J., YAN, A., XIE, N., FRANCISCO, M. L., & WONG, P. P. Y. (2025). AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions. In E. C. K. CHENG (Ed.), Innovating Education with AI : AETS 2024 (pp. 53-74). (Lecture Notes in Educational Technology; Vol. Part F312). Springer Singapore. https://doi.org/10.1007/978-981-96-4952-5_4

@inproceedings{8a8d2da9b3df4125b37c22f74fdf7379,

title = "AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions",

abstract = "The purpose of this study was to evaluate the effectiveness and relevance of AI-powered non-player characters (NPCs) in educational settings within the metaverse platform Classlet, particularly within the domain of applied social sciences. Integrating Speech Act Theory, Prospect Theory, and the Recognition-Primed Decision Model into AI prompt templates enhanced interactions and positively impacted student engagement. The AI NPCs achieved a performance ratio of 128%, providing contextually relevant responses effectively maintained by the prompt templates. A survey on students{\textquoteright} perceptions of the AI and VR integration revealed positive user perceptions, with strong correlations between enjoyment, perceived usefulness, and intent to use. Correlational analysis showed a strong fit (R2 = 0.816) for user intent, which had a mean of 74%. U-tests also indicated that female and non-VR users encountered more technical difficulties. Overall, the results suggest new ways of using AI and VR to promote learning engagement and interactions within applied social sciences.",

keywords = "Adaptive Learning Environments, AI Educational Agents, AI in Education",

author = "GONZALES, {Wilkinson Daniel Wong} and SHEN, {Daniel Jiandong} and Aihua YAN and Nina XIE and FRANCISCO, {Maria Leonora} and WONG, {Paulina Pui Yun}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.",

year = "2025",

month = apr,

day = "16",

doi = "10.1007/978-981-96-4952-5_4",

language = "English",

isbn = "9789819649518",

series = "Lecture Notes in Educational Technology",

publisher = "Springer Singapore",

pages = "53--74",

editor = "CHENG, {Eric C. K.}",

booktitle = "Innovating Education with AI : AETS 2024",

address = "Singapore",

}

GONZALES, WDW, SHEN, DJ, YAN, A , XIE, N, FRANCISCO, ML & WONG, PPY 2025, AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions. in ECK CHENG (ed.), Innovating Education with AI : AETS 2024. Lecture Notes in Educational Technology, vol. Part F312, Springer Singapore, pp. 53-74. https://doi.org/10.1007/978-981-96-4952-5_4

AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions. / GONZALES, Wilkinson Daniel Wong; SHEN, Daniel Jiandong; YAN, Aihua et al.
Innovating Education with AI : AETS 2024. ed. / Eric C. K. CHENG. Springer Singapore, 2025. p. 53-74 (Lecture Notes in Educational Technology; Vol. Part F312).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Referred Conference Paper › peer-review

TY - GEN

T1 - AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions

AU - GONZALES, Wilkinson Daniel Wong

AU - SHEN, Daniel Jiandong

AU - YAN, Aihua

AU - XIE, Nina

AU - FRANCISCO, Maria Leonora

AU - WONG, Paulina Pui Yun

PY - 2025/4/16

Y1 - 2025/4/16

N2 - The purpose of this study was to evaluate the effectiveness and relevance of AI-powered non-player characters (NPCs) in educational settings within the metaverse platform Classlet, particularly within the domain of applied social sciences. Integrating Speech Act Theory, Prospect Theory, and the Recognition-Primed Decision Model into AI prompt templates enhanced interactions and positively impacted student engagement. The AI NPCs achieved a performance ratio of 128%, providing contextually relevant responses effectively maintained by the prompt templates. A survey on students’ perceptions of the AI and VR integration revealed positive user perceptions, with strong correlations between enjoyment, perceived usefulness, and intent to use. Correlational analysis showed a strong fit (R2 = 0.816) for user intent, which had a mean of 74%. U-tests also indicated that female and non-VR users encountered more technical difficulties. Overall, the results suggest new ways of using AI and VR to promote learning engagement and interactions within applied social sciences.

AB - The purpose of this study was to evaluate the effectiveness and relevance of AI-powered non-player characters (NPCs) in educational settings within the metaverse platform Classlet, particularly within the domain of applied social sciences. Integrating Speech Act Theory, Prospect Theory, and the Recognition-Primed Decision Model into AI prompt templates enhanced interactions and positively impacted student engagement. The AI NPCs achieved a performance ratio of 128%, providing contextually relevant responses effectively maintained by the prompt templates. A survey on students’ perceptions of the AI and VR integration revealed positive user perceptions, with strong correlations between enjoyment, perceived usefulness, and intent to use. Correlational analysis showed a strong fit (R2 = 0.816) for user intent, which had a mean of 74%. U-tests also indicated that female and non-VR users encountered more technical difficulties. Overall, the results suggest new ways of using AI and VR to promote learning engagement and interactions within applied social sciences.

KW - Adaptive Learning Environments

KW - AI Educational Agents

KW - AI in Education

UR - http://www.scopus.com/inward/record.url?scp=105003009517&partnerID=8YFLogxK

U2 - 10.1007/978-981-96-4952-5_4

DO - 10.1007/978-981-96-4952-5_4

M3 - Conference paper (refereed)

SN - 9789819649518

T3 - Lecture Notes in Educational Technology

SP - 53

EP - 74

BT - Innovating Education with AI : AETS 2024

A2 - CHENG, Eric C. K.

PB - Springer Singapore

ER -

AI NPCs in an Educational Metaverse: Evaluating the Effectiveness of Prompt Templates for Contextual Interactions

Abstract

Publication series

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this