Deep learning(s) in gaming disorder through the user-avatar bond: A longitudinal study using machine learning
Journal of Behavioral Addictions · 2023
DOI: 10.1556/2006.2023.00062 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Behavioral Addictions, 2023. Verfasst von Vasileios Stavropoulos und 8 weiteren Autor:innen. Beteiligte Einrichtung: 1Department of Psychology, Applied Health, School of Health and Biomedical Sciences, RMIT University, Australia. Hauptthemen laut MEDLINE: Deep Learning, Behavior, Addictive, Video Games. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: RMIT University, Early Career Researcher Fund ECR 2020, Australian Research Council, Discovery Early Career Researcher Award, 2021.
Abstract (Originalsprache)
Background and aims Gaming disorder [GD] risk has been associated with the way gamers bond with their visual representation (i.e., avatar) in the game-world. More specifically, a gamer's relationship with their avatar has been shown to provide reliable mental health information about the user in their offline life, such as their current and prospective GD risk, if appropriately decoded.
Methods
To contribute to the paucity of knowledge in this area, 565 gamers ( M age = 29.3 years; SD =10.6) were assessed twice, six months apart, using the User-Avatar-Bond Scale (UABS) and the Gaming Disorder Test. A series of tuned and untuned artificial intelligence [AI] classifiers analysed concurrently and prospectively their responses.
Results
Findings showed that AI models learned to accurately and automatically identify GD risk cases, based on gamers' reported UABS score, age, and length of gaming involvement, both concurrently and longitudinally (i.e., six months later). Random forests outperformed all other AIs, while avatar immersion was shown to be the strongest training predictor.
Conclusion
Study outcomes demonstrated that the user-avatar bond can be translated into accurate, concurrent and future GD risk predictions using trained AI classifiers. Assessment, prevention, and practice implications are discussed in the light of these findings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- 1Department of Psychology, Applied Health, School of Health and Biomedical Sciences, RMIT University, Australia.
- 3National and Kapodistrian University of Athens, Greece.
- 2Victoria University, Australia.
- 4The Three Seas Psychology, Australia.
- 5Catholic Care Victoria, Australia.
- 6Mighty Serious, Australia.
ORCID-Profile: Vasileios Stavropoulos, Daniel Zarate, Maria Prokofieva, Leila Karimi, Mark D Griffiths
Förderung
- RMIT University, Early Career Researcher Fund ECR 2020
- Australian Research Council, Discovery Early Career Researcher Award, 2021
Zitieren
APA
Stavropoulos, V., Zarate, D., Prokofieva, M., Van de Berg, N., Karimi, L., Gorman Alesi, A., Richards, M., Bennet, S., & Griffiths, M. D. (2023). Deep learning(s) in gaming disorder through the user-avatar bond: A longitudinal study using machine learning. Journal of Behavioral Addictions. https://doi.org/10.1556/2006.2023.00062
Vancouver
Stavropoulos V, Zarate D, Prokofieva M, Van de Berg N, Karimi L, Gorman Alesi A, et al. Deep learning(s) in gaming disorder through the user-avatar bond: A longitudinal study using machine learning. Journal of Behavioral Addictions. 2023. doi:10.1556/2006.2023.00062
BibTeX
@article{Stavropoulos2023,
author = {Stavropoulos, Vasileios and Zarate, Daniel and Prokofieva, Maria and Van de Berg, Noirin and Karimi, Leila and Gorman Alesi, Angela and Richards, Michaella and Bennet, Soula and Griffiths, Mark D},
title = {Deep learning(s) in gaming disorder through the user-avatar bond: A longitudinal study using machine learning},
journal = {Journal of Behavioral Addictions},
year = {2023},
doi = {10.1556/2006.2023.00062}
}
EUVIMED