LightGCN Based Prediction Model of Anxiety Risk from Adolescent Social Network Behaviors
- DOI
- 10.2991/978-2-38476-553-9_47How to use a DOI?
- Keywords
- LightGCN; Adolescent Psychology; Social Network Analysis; Anxiety Prediction; Cross-Modal Fusion
- Abstract
With the growing prevalence of adolescent social media usage, the relationship between online interaction behaviors and psychological health has become a critical research topic. This paper proposes a LightGCN-based prediction model to assess anxiety risk from social network behaviors. The dataset combines structured features (interaction frequency, network centrality, and temporal activity) with unstructured textual data from online mental health questionnaires. By integrating cross-modal feature fusion, the model captures both the topological and semantic dimensions of user behaviors. Experimental results demonstrate that the proposed model achieves superior prediction accuracy compared with traditional machine learning baselines, offering a new approach for early psychological screening and digital mental health intervention.
- Copyright
- © 2026 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Zhiyi Xu PY - 2026 DA - 2026/03/25 TI - LightGCN Based Prediction Model of Anxiety Risk from Adolescent Social Network Behaviors BT - Proceedings of the 2025 4th International Conference on Educational Science and Social Culture (ESSC 2025) PB - Atlantis Press SP - 412 EP - 418 SN - 2352-5398 UR - https://doi.org/10.2991/978-2-38476-553-9_47 DO - 10.2991/978-2-38476-553-9_47 ID - Xu2026 ER -