Federated learning for privacy-preserving depression detection with multilingual language models in social media posts
Patterns · 2024-07 · 5 (7) · 100990
DOI: 10.1016/j.patter.2024.100990 ↗Kurz gefasst
Fachartikel in der Zeitschrift Patterns, 2024-07. Verfasst von Samar Samir Khalil und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering Department, Arab Academy for Science, Technology and Maritime Transport, Alexandria, Egypt. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universiteit Leiden.
Themen: Depression
Abstract (Originalsprache)
The incidences of mental health illnesses, such as suicidal ideation and depression, are increasing, which highlights the urgent need for early detection methods. There is a growing interest in using natural language processing (NLP) models to analyze textual data from patients, but accessing patients' data for research purposes can be challenging due to privacy concerns. Federated learning (FL) is a promising approach that can balance the need for centralized learning with data ownership sensitivity. In this study, we examine the effectiveness of FL models in detecting depression by using a simulated multilingual dataset. We analyzed social media posts in five different languages with varying sample sizes. Our findings indicate that FL achieves strong performance in most cases while maintaining clients' privacy for both independent and non-independent client partitioning.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Engineering Department, Arab Academy for Science, Technology and Maritime Transport, Alexandria, Egypt.
- Leiden Institute of Advanced Computer Science, Leiden University, 2333 CA Leiden, the Netherlands.
- Public Health & Primary Care, Leiden University Medical Center, 2333 CA Leiden, the Netherlands.
Förderung
- Universiteit Leiden
Zitieren
APA
Khalil, S. S., Tawfik, N. S., & Spruit, M. (2024). Federated learning for privacy-preserving depression detection with multilingual language models in social media posts. Patterns, 5(7), 100990. https://doi.org/10.1016/j.patter.2024.100990
Vancouver
Khalil SS, Tawfik NS, Spruit M. Federated learning for privacy-preserving depression detection with multilingual language models in social media posts. Patterns. 2024;5(7):100990. doi:10.1016/j.patter.2024.100990
BibTeX
@article{Khalil2024,
author = {Khalil, Samar Samir and Tawfik, Noha S and Spruit, Marco},
title = {Federated learning for privacy-preserving depression detection with multilingual language models in social media posts},
journal = {Patterns},
year = {2024},
volume = {5},
number = {7},
pages = {100990},
doi = {10.1016/j.patter.2024.100990}
}
EUVIMED