Home > Research > Publications & Outputs > Exploring the Suitability of Transformer Models...

Electronic data

  • 2024.cl4health-1.22

    Final published version, 259 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

View graph of relations

Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation. / Coole, Matthew; Rayson, Paul; Glossop, Zoe et al.
Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024. ed. / Dina Demner-Fushman; Sophia Ananiadou; Paul Thompson; Brian Ondov. Torino, Italia: ELRA and ICCL, 2024. p. 184-188.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Coole, M, Rayson, P, Glossop, Z, Lobban, F, Marshall, P & Vidler, J 2024, Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation. in D Demner-Fushman, S Ananiadou, P Thompson & B Ondov (eds), Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024. ELRA and ICCL, Torino, Italia, pp. 184-188. <https://aclanthology.org/2024.cl4health-1.22>

APA

Coole, M., Rayson, P., Glossop, Z., Lobban, F., Marshall, P., & Vidler, J. (2024). Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation. In D. Demner-Fushman, S. Ananiadou, P. Thompson, & B. Ondov (Eds.), Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024 (pp. 184-188). ELRA and ICCL. https://aclanthology.org/2024.cl4health-1.22

Vancouver

Coole M, Rayson P, Glossop Z, Lobban F, Marshall P, Vidler J. Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation. In Demner-Fushman D, Ananiadou S, Thompson P, Ondov B, editors, Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024. Torino, Italia: ELRA and ICCL. 2024. p. 184-188

Author

Coole, Matthew ; Rayson, Paul ; Glossop, Zoe et al. / Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation. Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024. editor / Dina Demner-Fushman ; Sophia Ananiadou ; Paul Thompson ; Brian Ondov. Torino, Italia : ELRA and ICCL, 2024. pp. 184-188

Bibtex

@inproceedings{a65e3d9225e540a6afa79d84daf8caa6,
title = "Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation",
abstract = "Mental health peer support forums have become widely used in recent years. The emerging mental health crisis and the COVID-19 pandemic have meant that finding a place online for support and advice when dealing with mental health issues is more critical than ever. The need to examine, understand and find ways to improve the support provided by mental health forums is vital in the current climate. As part of this, we present our initial explorations in using modern transformer models to detect four key concepts (connectedness, lived experience, empathy and gratitude), which we believe are essential to understanding how people use mental health forums and will serve as a basis for testing more expansive realise theories about mental health forums in the future. As part of this work, we also replicate previously published results on empathy utilising an existing annotated dataset and test the other concepts on our manually annotated mental health forum posts dataset. These results serve as a basis for future research examining peer support forums.",
author = "Matthew Coole and Paul Rayson and Zoe Glossop and Fiona Lobban and Paul Marshall and John Vidler",
year = "2024",
month = may,
day = "1",
language = "English",
pages = "184--188",
editor = "Dina Demner-Fushman and Sophia Ananiadou and Paul Thompson and Brian Ondov",
booktitle = "Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024",
publisher = "ELRA and ICCL",

}

RIS

TY - GEN

T1 - Exploring the Suitability of Transformer Models to Analyse Mental Health Peer Support Forum Data for a Realist Evaluation

AU - Coole, Matthew

AU - Rayson, Paul

AU - Glossop, Zoe

AU - Lobban, Fiona

AU - Marshall, Paul

AU - Vidler, John

PY - 2024/5/1

Y1 - 2024/5/1

N2 - Mental health peer support forums have become widely used in recent years. The emerging mental health crisis and the COVID-19 pandemic have meant that finding a place online for support and advice when dealing with mental health issues is more critical than ever. The need to examine, understand and find ways to improve the support provided by mental health forums is vital in the current climate. As part of this, we present our initial explorations in using modern transformer models to detect four key concepts (connectedness, lived experience, empathy and gratitude), which we believe are essential to understanding how people use mental health forums and will serve as a basis for testing more expansive realise theories about mental health forums in the future. As part of this work, we also replicate previously published results on empathy utilising an existing annotated dataset and test the other concepts on our manually annotated mental health forum posts dataset. These results serve as a basis for future research examining peer support forums.

AB - Mental health peer support forums have become widely used in recent years. The emerging mental health crisis and the COVID-19 pandemic have meant that finding a place online for support and advice when dealing with mental health issues is more critical than ever. The need to examine, understand and find ways to improve the support provided by mental health forums is vital in the current climate. As part of this, we present our initial explorations in using modern transformer models to detect four key concepts (connectedness, lived experience, empathy and gratitude), which we believe are essential to understanding how people use mental health forums and will serve as a basis for testing more expansive realise theories about mental health forums in the future. As part of this work, we also replicate previously published results on empathy utilising an existing annotated dataset and test the other concepts on our manually annotated mental health forum posts dataset. These results serve as a basis for future research examining peer support forums.

M3 - Conference contribution/Paper

SP - 184

EP - 188

BT - Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024

A2 - Demner-Fushman, Dina

A2 - Ananiadou, Sophia

A2 - Thompson, Paul

A2 - Ondov, Brian

PB - ELRA and ICCL

CY - Torino, Italia

ER -