Game Reviews Reviewed: A Game Designer’s Perspective on AI-generated Game Review Analyses

Michael Lankes; Andreas Stöckl

doi:10.1109/CoG57401.2023.10333238

Game Reviews Reviewed: A Game Designer’s Perspective on AI-generated Game Review Analyses

Michael Lankes, Andreas Stöckl

Publikation: Beitrag in Buch/Bericht/Tagungsband › Konferenzbeitrag › Begutachtung

2 Zitate (Scopus)

Abstract

Due to the growing number of available games, game reviews provide a vital basis for decision-making when buying a game. Apart from that, these reviews could serve as a rich design resource and inspiration for game designers. In this paper, we analyze game reviews formulated by players via a large language model and ask GPT-3, an artificial intelligence, game design-related questions based on the Player Experience Inventory (PXI) questionnaire. The obtained results are evaluated in expert interviews, where we asked four indie game designers about the quality of the game review analyses. The experts were generally impressed by the AI-generated texts but also provided some recommendations regarding the game review analyses’ quality, structure, and setup.

Originalsprache	Englisch
Titel	Proceedings of the 2023 IEEE Conference on Games, CoG 2023
Seiten	1-8
Seitenumfang	8
ISBN (elektronisch)	9798350322774
DOIs	https://doi.org/10.1109/CoG57401.2023.10333238
Publikationsstatus	Veröffentlicht - Dez. 2023

Publikationsreihe

Name	IEEE Conference on Computatonal Intelligence and Games, CIG
ISSN (Print)	2325-4270
ISSN (elektronisch)	2325-4289

Zugriff auf Dokument

10.1109/CoG57401.2023.10333238

Andere Dateien und Links

Link zur Publikation in Scopus

Zitieren

@inproceedings{4102a4018ff0442ea65f340f31f41659,

title = "Game Reviews Reviewed: A Game Designer{\textquoteright}s Perspective on AI-generated Game Review Analyses",

abstract = "Due to the growing number of available games, game reviews provide a vital basis for decision-making when buying a game. Apart from that, these reviews could serve as a rich design resource and inspiration for game designers. In this paper, we analyze game reviews formulated by players via a large language model and ask GPT-3, an artificial intelligence, game design-related questions based on the Player Experience Inventory (PXI) questionnaire. The obtained results are evaluated in expert interviews, where we asked four indie game designers about the quality of the game review analyses. The experts were generally impressed by the AI-generated texts but also provided some recommendations regarding the game review analyses{\textquoteright} quality, structure, and setup.",

keywords = "GPT-3, artificial intelligence, game design, game reviews, language models",

author = "Michael Lankes and Andreas St{\"o}ckl",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.",

year = "2023",

month = dec,

doi = "10.1109/CoG57401.2023.10333238",

language = "English",

series = "IEEE Conference on Computatonal Intelligence and Games, CIG",

pages = "1--8",

booktitle = "Proceedings of the 2023 IEEE Conference on Games, CoG 2023",

}

TY - GEN

T1 - Game Reviews Reviewed: A Game Designer’s Perspective on AI-generated Game Review Analyses

AU - Lankes, Michael

AU - Stöckl, Andreas

PY - 2023/12

Y1 - 2023/12

N2 - Due to the growing number of available games, game reviews provide a vital basis for decision-making when buying a game. Apart from that, these reviews could serve as a rich design resource and inspiration for game designers. In this paper, we analyze game reviews formulated by players via a large language model and ask GPT-3, an artificial intelligence, game design-related questions based on the Player Experience Inventory (PXI) questionnaire. The obtained results are evaluated in expert interviews, where we asked four indie game designers about the quality of the game review analyses. The experts were generally impressed by the AI-generated texts but also provided some recommendations regarding the game review analyses’ quality, structure, and setup.

AB - Due to the growing number of available games, game reviews provide a vital basis for decision-making when buying a game. Apart from that, these reviews could serve as a rich design resource and inspiration for game designers. In this paper, we analyze game reviews formulated by players via a large language model and ask GPT-3, an artificial intelligence, game design-related questions based on the Player Experience Inventory (PXI) questionnaire. The obtained results are evaluated in expert interviews, where we asked four indie game designers about the quality of the game review analyses. The experts were generally impressed by the AI-generated texts but also provided some recommendations regarding the game review analyses’ quality, structure, and setup.

KW - GPT-3

KW - artificial intelligence

KW - game design

KW - game reviews

KW - language models

UR - http://www.scopus.com/inward/record.url?scp=85180546886&partnerID=8YFLogxK

U2 - 10.1109/CoG57401.2023.10333238

DO - 10.1109/CoG57401.2023.10333238

M3 - Conference contribution

T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

SP - 1

EP - 8

BT - Proceedings of the 2023 IEEE Conference on Games, CoG 2023

ER -