Postgraduate psychological stress detection from social media using BERT-Fused model
PLOS ONE · 31.10.2024 · 19 (10) · e0312264
DOI: 10.1371/journal.pone.0312264 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 31.10.2024. Verfasst von Muni Zhuang und 3 weiteren Autor:innen. Beteiligte Einrichtung: National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian, China. Hauptthemen laut MEDLINE: Social Media, Stress, Psychological. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Shenzhen Basic Research Project for Development of Science and Technology, The Innovation Team Project of Colleges in Guangdong Province, The Natural Science Foundation of Guangdong Province.
Abstract (Originalsprache)
Postgraduate students face various academic, personal, and social stressors that increase their risk of anxiety, depression, and suicide. Identifying cost-effective methods of detecting and intervening before stress turns into severe problems is crucial. However, existing stress detection methods typically rely on psychological scales or devices, which can be complex and expensive. Therefore, we propose a BERT-fused model for rapidly and automatically detecting postgraduate students’ psychological stress via social media. First, we construct an improved BERT-LDA feature extraction algorithm to extract group stress features from large-scale and complex social media data. Then, we integrate the BiLSTM-CRF named entity recognition model to construct a multi-dimensional psychological stress profil e and analyze the fine-grained feature representation under the fusion of multi-dimensional features. Experimental results demonstrate that the proposed model outperforms traditional models such as BiLSTM, achieving an accuracy of 92.55%, a recall of 93.47%, and an F1-score of 92.18%, with F1-scores exceeding 89% for all three types of entities. This research provides both theoretical and practical foundations for universities or institutions to conduct fine-grained perception and intervention for postgraduate students’ psychological stress.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- National Institute for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian, China.
- School of Medicine, Xiamen University, Xiamen, Fujian, China.
- Shenzhen Institute of Information Technology, School of Software Engineering, Shenzhen, Guangdong, China.
- College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China.
- Shenzhen Institute of Information Technology, Career-Oriented Multidisciplinary Education Center, Shenzhen, Guangdong, China.
ORCID-Profile: Muni Zhuang, Xu Tan
Förderung
- The Shenzhen Basic Research Project for Development of Science and Technology
- The Innovation Team Project of Colleges in Guangdong Province
- The Natural Science Foundation of Guangdong Province
Zitieren
APA
Zhuang, M., Cheng, D., Lu, X., & Tan, X. (2024). Postgraduate psychological stress detection from social media using BERT-Fused model. PLOS ONE, 19(10), e0312264. https://doi.org/10.1371/journal.pone.0312264
Vancouver
Zhuang M, Cheng D, Lu X, Tan X. Postgraduate psychological stress detection from social media using BERT-Fused model. PLOS ONE. 2024;19(10):e0312264. doi:10.1371/journal.pone.0312264
BibTeX
@article{Zhuang2024,
author = {Zhuang, Muni and Cheng, Dongsheng and Lu, Xin and Tan, Xu},
title = {Postgraduate psychological stress detection from social media using BERT-Fused model},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {10},
pages = {e0312264},
doi = {10.1371/journal.pone.0312264}
}
EUVIMED