Clustering digital mental health perceptions using transformer-based models
The rise in online mental health discussions underscores the need to understand diverse perspectives to inform targeted interventions. Addressing the granularity of existing research on mapping such perspectives, this study proposes a model combining contextual and sentiment analysis, keyword scorin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Franklin Open |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773186325000520 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849423683279388672 |
|---|---|
| author | Ayodeji O.J. Ibitoye Oladosu O. Oladimeji Oluwaseyi F. Afe |
| author_facet | Ayodeji O.J. Ibitoye Oladosu O. Oladimeji Oluwaseyi F. Afe |
| author_sort | Ayodeji O.J. Ibitoye |
| collection | DOAJ |
| description | The rise in online mental health discussions underscores the need to understand diverse perspectives to inform targeted interventions. Addressing the granularity of existing research on mapping such perspectives, this study proposes a model combining contextual and sentiment analysis, keyword scoring, and clustering techniques to identify themes in online comments. Using transformer-based models (BERT, ALBERT, ELECTRA), the study achieved high-quality clustering of seven distinct mental health perspectives: stigma, empowerment, treatment approaches, recovery, social/environmental factors, advocacy, and cultural dimensions. ELECTRA outperformed others in clustering quality (silhouette score: 0.73; Davies-Bouldin Index: 0.34). The findings reveal cohesive, well-separated clusters that enhance understanding of digital mental health discourse. These insights provide a foundation for data-driven advocacy, tailored interventions, and broader awareness, addressing the complex dynamics of mental health narratives in online spaces. This study bridges a critical research gap by offering a systematic approach to analysing and interpreting mental health perspectives in digital environments. |
| format | Article |
| id | doaj-art-ab9f5cb29bbd4fe5b4b26140529477eb |
| institution | Kabale University |
| issn | 2773-1863 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Franklin Open |
| spelling | doaj-art-ab9f5cb29bbd4fe5b4b26140529477eb2025-08-20T03:30:32ZengElsevierFranklin Open2773-18632025-06-011110026210.1016/j.fraope.2025.100262Clustering digital mental health perceptions using transformer-based modelsAyodeji O.J. Ibitoye0Oladosu O. Oladimeji1Oluwaseyi F. Afe2School of Computing and Mathematical Sciences, University of Greenwich, London, United Kingdom; Corresponding author at: School of Computing and Mathematical Sciences, University of Greenwich, London.Faculty of Engineering and Design, Atlantic Technological University, Sligo, IrelandDepartment of Computer Science, Lead City University, Ibadan, NigeriaThe rise in online mental health discussions underscores the need to understand diverse perspectives to inform targeted interventions. Addressing the granularity of existing research on mapping such perspectives, this study proposes a model combining contextual and sentiment analysis, keyword scoring, and clustering techniques to identify themes in online comments. Using transformer-based models (BERT, ALBERT, ELECTRA), the study achieved high-quality clustering of seven distinct mental health perspectives: stigma, empowerment, treatment approaches, recovery, social/environmental factors, advocacy, and cultural dimensions. ELECTRA outperformed others in clustering quality (silhouette score: 0.73; Davies-Bouldin Index: 0.34). The findings reveal cohesive, well-separated clusters that enhance understanding of digital mental health discourse. These insights provide a foundation for data-driven advocacy, tailored interventions, and broader awareness, addressing the complex dynamics of mental health narratives in online spaces. This study bridges a critical research gap by offering a systematic approach to analysing and interpreting mental health perspectives in digital environments.http://www.sciencedirect.com/science/article/pii/S2773186325000520Mental healthText clusteringTransformer-based architecturesDecision supportMental health perspectivesDigital mental health |
| spellingShingle | Ayodeji O.J. Ibitoye Oladosu O. Oladimeji Oluwaseyi F. Afe Clustering digital mental health perceptions using transformer-based models Franklin Open Mental health Text clustering Transformer-based architectures Decision support Mental health perspectives Digital mental health |
| title | Clustering digital mental health perceptions using transformer-based models |
| title_full | Clustering digital mental health perceptions using transformer-based models |
| title_fullStr | Clustering digital mental health perceptions using transformer-based models |
| title_full_unstemmed | Clustering digital mental health perceptions using transformer-based models |
| title_short | Clustering digital mental health perceptions using transformer-based models |
| title_sort | clustering digital mental health perceptions using transformer based models |
| topic | Mental health Text clustering Transformer-based architectures Decision support Mental health perspectives Digital mental health |
| url | http://www.sciencedirect.com/science/article/pii/S2773186325000520 |
| work_keys_str_mv | AT ayodejiojibitoye clusteringdigitalmentalhealthperceptionsusingtransformerbasedmodels AT oladosuooladimeji clusteringdigitalmentalhealthperceptionsusingtransformerbasedmodels AT oluwaseyifafe clusteringdigitalmentalhealthperceptionsusingtransformerbasedmodels |