Deep learning(s) in gaming disorder through the user-avatar bond: A longitudinal study using machine learning.

Area of Science:

• Psychology
• Computer Science
• Mental Health

Background:

• Gaming disorder (GD) risk is linked to the gamer's bond with their in-game avatar.
• The user-avatar relationship can offer insights into a gamer's mental health and GD risk.

Purpose of the Study:

• To investigate the predictive power of the user-avatar bond on gaming disorder risk.
• To explore the use of artificial intelligence (AI) in assessing concurrent and prospective GD risk.

Main Methods:

• 565 gamers were assessed twice over six months using the User-Avatar-Bond Scale (UABS) and the Gaming Disorder Test.
• Tuned and untuned AI classifiers analyzed gamer responses for concurrent and longitudinal GD risk prediction.

Main Results:

• AI models accurately identified GD risk based on UABS scores, age, and gaming duration.
• Avatar immersion was the strongest predictor in AI models; random forests showed superior performance.
• AI successfully predicted GD risk concurrently and up to six months prospectively.

Conclusions:

• The user-avatar bond is a significant factor in predicting gaming disorder risk.
• AI classifiers can effectively translate user-avatar bond metrics into actionable GD risk assessments.
• Findings support implications for GD assessment, prevention, and intervention strategies.