Cross-sectional classification of mental health risk indicators in university students using graph convolutional networks: The Atrisk-GCN framework
Computer Science and Information Systems · 2026 · (00) · 53-53
DOI: 10.2298/csis260725053m ↗Kurz gefasst
Querschnittstudie in der Zeitschrift Computer Science and Information Systems, 2026. Verfasst von Seifeddine Mechti und 7 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Identifying students at psychological risk is a growing public-health concern in higher education. Conventional self-report questionnaires are subject to response bias and provide only static snapshots of mental health status. Graph Convolutional Networks (GCNs) offer a principled way to model feature-based relational similarities between individuals, going beyond independent-sample assumptions made by classical classifiers. In this paper we present AtRisk-GCN, a GCN-based framework for cross-sectional classification of questionnaire-derived and text-derived mental-health risk indicators in student populations. Two datasets are studied: (i) a survey-derived dataset of 1 000 records, comprising real medical students from a single institution (Faculty of Biology and Medicine, University of Lausanne, and Lausanne University Hospital, CHUV, Switzerland), drawn from the publicly available data release accompanying Carrard et al. [5]) (Data 1, continuous psychological scale scores as node features) and (ii) a publicly available mental-health text corpus of 27 977 samples (Data 2, TF-IDF representations as node features, no synthetic augmentation). In both cases, edges are constructed from cosine-similarity between node feature vectors using a k-nearest-neighbour (k-NN) scheme; no observed social-network data are available or assumed. On Data 1, AtRisk-GCN achieves an accuracy of 0.861 and an F1-score of 0.857, outperforming LSTM, CNN, and Transformer baselines. On Data 2 the model attains 0.84 accuracy and an F1-score of 0.84, surpassing, under matched input representation, TF-IDFbased Logistic Regression and Linear SVM baselines, and clearly outperforming the graph-free MLP trained on identical feature.
Zitieren
APA
Mechti, S., Saddoud, A., Allouch, A., Sassi, S., Chbeir, R., Brahmi, H., Ammar, B., & Chlif, M. (2026). Cross-sectional classification of mental health risk indicators in university students using graph convolutional networks: The Atrisk-GCN framework. Computer Science and Information Systems, 53-53. https://doi.org/10.2298/csis260725053m
Vancouver
Mechti S, Saddoud A, Allouch A, Sassi S, Chbeir R, Brahmi H, et al. Cross-sectional classification of mental health risk indicators in university students using graph convolutional networks: The Atrisk-GCN framework. Computer Science and Information Systems. 2026:53-53. doi:10.2298/csis260725053m
BibTeX
@article{Mechti2026,
author = {Mechti, Seifeddine and Saddoud, Anis and Allouch, Azza and Sassi, Salma and Chbeir, Richard and Brahmi, Hajer and Ammar, Boudour and Chlif, Mehdi},
title = {Cross-sectional classification of mental health risk indicators in university students using graph convolutional networks: The Atrisk-GCN framework},
journal = {Computer Science and Information Systems},
year = {2026},
number = {00},
pages = {53--53},
doi = {10.2298/csis260725053m}
}
EUVIMED