Comorbidity in Internet Gaming Disorder: An Embedding-Based Topic Modeling Analysis.

Authors

Misong Woo, Gangta Choi, Hyunchan Hwang, Doug Hyun Han

Published in

European addiction research. Pages 1. Aug 31, 2026. Epub Aug 31, 2026.

Abstract

Background Internet Gaming Disorder frequently co-occurs with psychiatric conditions, yet many studies overlook these comorbidities, leading to oversimplified interpretations Objectives This study systematically examined thematic and interpretative differences in IGD research according to whether psychiatric comorbidities were explicitly incorporated. Method We analyzed 1,201 IGD-related articles, classified into With Comorbidity (WC; n = 21) and Without Comorbidity (WoC; n = 1,180) groups. After text preprocessing, BERTopic modeling was performed to identify and compare thematic structures. For the WoC group, topics were further classified as "psychiatric-related" if they contained at least two predefined psychiatric disorder keywords. For the WC group, the influence of comorbidity on outcome interpretation was evaluated. We implemented an AI-assisted Natural Language Processing pipeline to compare thematic structure across groups. Results Topic modeling identified 26 topics in WoC and 5 in WC. WoC topics covered diverse themes, whilst WC topics highlighted clinical interactions involving comorbidities such as ADHD, anxiety, and depression. In the WC group, 81% of studies showed that comorbidity significantly influenced outcome interpretations. To statistically compare the distribution of two groups, we performed centroid alignment with a correction factor based on the word-count ratio. Maximum mean discrepancy (MMD) analysis confirmed a significant difference in semantic distribution after correction (MMD distance=1.24*10^-4, p=0.02).Conclusions Explicit consideration of psychiatric comorbidities enhances the clinical and interpretative accuracy of IGD research. Future studies should systematically integrate comorbidity analyses to improve understanding and therapeutic management of IGD. The AI-assisted NLP synthesis offers a scalable evidence-mapping approach to identify clinically relevant gaps and biases in the IGD literature, particularly regarding psychiatric comorbidity.

PMID:
42671973
Bibliographic data and abstract were imported from PubMed on 01 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.