BERT-Based Transformers for Early Detection of Mental Health Illnesses

Rodrigo Martínez-Castaño; Amal Htait; Leif Azzopardi; Yashar Moshfeghi

doi:10.1007/978-3-030-85251-1_15

BERT-Based Transformers for Early Detection of Mental Health Illnesses

Rodrigo Martínez-Castaño, Amal Htait, Leif Azzopardi, Yashar Moshfeghi

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

This paper briefly describes our research groups' efforts in tackling Task 1 (Early Detection of Signs of Self-Harm), and Task 2 (Measuring the Severity of the Signs of Depression) from the CLEF eRisk Track. Core to how we approached these problems was the use of BERT-based classifiers which were trained specifically for each task. Our results on both tasks indicate that this approach delivers high performance across a series of measures, particularly for Task 1, where our submissions obtained the best performance for precision, F1, latency-weighted F1 and ERDE at 5 and 50. This work suggests that BERT-based classifiers, when trained appropriately, can accurately infer which social media users are at risk of self-harming, with precision up to 91.3% for Task 1. Given these promising results, it will be interesting to further refine the training regime, classifier and early detection scoring mechanism, as well as apply the same approach to other related tasks (e.g., anorexia, depression, suicide).

Original language	English
Title of host publication	Experimental IR Meets Multilinguality, Multimodality, and Interaction
Subtitle of host publication	12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings
Editors	K. Selçuk Candan, Bogdan Ionescu, Lorraine Goeuriot, Birger Larsen, Henning Mueller, Alexis Joly, Maria Maistro, Florina Piroi, Guglielmo Faggioli, Nicolo Ferro
Chapter	15
Pages	189-200
ISBN (Electronic)	9783030852511
DOIs	https://doi.org/10.1007/978-3-030-85251-1_15
Publication status	Published - 14 Sept 2021
Event	12th International Conference of the CLEF Association - Virtual Event Duration: 21 Sept 2021 → 24 Sept 2021

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	12880
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	12th International Conference of the CLEF Association
Abbreviated title	CLEF 2021
Period	21/09/21 → 24/09/21

Bibliographical note

Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Acknowledgements & Funding: The first author would like to thank the following funding bod-
ies for their support: FEDER/Ministerio de Ciencia, Innovaci ́on y Universidades, Agencia Estatal de Investigaci ́on/Project (RTI2018-093336-B-C21), Conseller ́ıa de Educacion, Universidade e Formaci ́on Profesional and the European Regional DevelopmentFund (ERDF) (accreditation 2019–2022 ED431G-2019/04, ED431C 2018/29, ED431C2018/19). The second and third authors would like to thank the UKRI’s EPSRC Project Cumulative Revelations in Personal Data (Grant Number: EP/R033897/1) for theirsupport. They would also like to thank David Losada for arranging this collaboration.

Keywords

Self-harm
Depression
Classification
Social media
Early detection
BERT
XLM-RoBERTa

Access to Document

10.1007/978-3-030-85251-1_15Licence: CC BY 4.0

Martinez-Castano et al_BERT-Based Transformers for Early Detection of Mental Health Illnesses_978-3-030-85251-1_15
Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Licence: CC BY 4.0

Cite this

Martínez-Castaño, R., Htait, A., Azzopardi, L., & Moshfeghi, Y. (2021). BERT-Based Transformers for Early Detection of Mental Health Illnesses. In K. S. Candan, B. Ionescu, L. Goeuriot, B. Larsen, H. Mueller, A. Joly, M. Maistro, F. Piroi, G. Faggioli, & N. Ferro (Eds.), Experimental IR Meets Multilinguality, Multimodality, and Interaction: 12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings (pp. 189-200). (Lecture Notes in Computer Science; Vol. 12880). https://doi.org/10.1007/978-3-030-85251-1_15

Martínez-Castaño, Rodrigo ; Htait, Amal ; Azzopardi, Leif et al. / BERT-Based Transformers for Early Detection of Mental Health Illnesses. Experimental IR Meets Multilinguality, Multimodality, and Interaction: 12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings. editor / K. Selçuk Candan ; Bogdan Ionescu ; Lorraine Goeuriot ; Birger Larsen ; Henning Mueller ; Alexis Joly ; Maria Maistro ; Florina Piroi ; Guglielmo Faggioli ; Nicolo Ferro. 2021. pp. 189-200 (Lecture Notes in Computer Science).

@inproceedings{3acf5cea4f34459ea280494fd4c74aef,

title = "BERT-Based Transformers for Early Detection of Mental Health Illnesses",

abstract = "This paper briefly describes our research groups' efforts in tackling Task 1 (Early Detection of Signs of Self-Harm), and Task 2 (Measuring the Severity of the Signs of Depression) from the CLEF eRisk Track. Core to how we approached these problems was the use of BERT-based classifiers which were trained specifically for each task. Our results on both tasks indicate that this approach delivers high performance across a series of measures, particularly for Task 1, where our submissions obtained the best performance for precision, F1, latency-weighted F1 and ERDE at 5 and 50. This work suggests that BERT-based classifiers, when trained appropriately, can accurately infer which social media users are at risk of self-harming, with precision up to 91.3% for Task 1. Given these promising results, it will be interesting to further refine the training regime, classifier and early detection scoring mechanism, as well as apply the same approach to other related tasks (e.g., anorexia, depression, suicide).",

keywords = "Self-harm, Depression, Classification, Social media, Early detection, BERT, XLM-RoBERTa",

author = "Rodrigo Mart{\'i}nez-Casta{\~n}o and Amal Htait and Leif Azzopardi and Yashar Moshfeghi",

note = "Copyright {\textcopyright} 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Acknowledgements & Funding: The first author would like to thank the following funding bod- ies for their support: FEDER/Ministerio de Ciencia, Innovaci{\' }on y Universidades, Agencia Estatal de Investigaci{\' }on/Project (RTI2018-093336-B-C21), Conseller{\' }ıa de Educacion, Universidade e Formaci{\' }on Profesional and the European Regional DevelopmentFund (ERDF) (accreditation 2019–2022 ED431G-2019/04, ED431C 2018/29, ED431C2018/19). The second and third authors would like to thank the UKRI{\textquoteright}s EPSRC Project Cumulative Revelations in Personal Data (Grant Number: EP/R033897/1) for theirsupport. They would also like to thank David Losada for arranging this collaboration.; 12th International Conference of the CLEF Association, CLEF 2021 ; Conference date: 21-09-2021 Through 24-09-2021",

year = "2021",

month = sep,

day = "14",

doi = "10.1007/978-3-030-85251-1_15",

language = "English",

isbn = "9783030852504",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "189--200",

editor = "Candan, {K. Sel{\c c}uk} and Bogdan Ionescu and Lorraine Goeuriot and Birger Larsen and Henning Mueller and Alexis Joly and Maria Maistro and Florina Piroi and Faggioli, {Guglielmo } and Nicolo Ferro",

booktitle = "Experimental IR Meets Multilinguality, Multimodality, and Interaction",

}

Martínez-Castaño, R, Htait, A, Azzopardi, L & Moshfeghi, Y 2021, BERT-Based Transformers for Early Detection of Mental Health Illnesses. in KS Candan, B Ionescu, L Goeuriot, B Larsen, H Mueller, A Joly, M Maistro, F Piroi, G Faggioli & N Ferro (eds), Experimental IR Meets Multilinguality, Multimodality, and Interaction: 12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings. Lecture Notes in Computer Science, vol. 12880, pp. 189-200, 12th International Conference of the CLEF Association, 21/09/21. https://doi.org/10.1007/978-3-030-85251-1_15

BERT-Based Transformers for Early Detection of Mental Health Illnesses. / Martínez-Castaño, Rodrigo; Htait, Amal; Azzopardi, Leif et al.
Experimental IR Meets Multilinguality, Multimodality, and Interaction: 12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings. ed. / K. Selçuk Candan; Bogdan Ionescu; Lorraine Goeuriot; Birger Larsen; Henning Mueller; Alexis Joly; Maria Maistro; Florina Piroi; Guglielmo Faggioli; Nicolo Ferro. 2021. p. 189-200 (Lecture Notes in Computer Science; Vol. 12880).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - BERT-Based Transformers for Early Detection of Mental Health Illnesses

AU - Martínez-Castaño, Rodrigo

AU - Htait, Amal

AU - Azzopardi, Leif

AU - Moshfeghi, Yashar

N1 - Copyright © 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Acknowledgements & Funding: The first author would like to thank the following funding bod- ies for their support: FEDER/Ministerio de Ciencia, Innovaci ́on y Universidades, Agencia Estatal de Investigaci ́on/Project (RTI2018-093336-B-C21), Conseller ́ıa de Educacion, Universidade e Formaci ́on Profesional and the European Regional DevelopmentFund (ERDF) (accreditation 2019–2022 ED431G-2019/04, ED431C 2018/29, ED431C2018/19). The second and third authors would like to thank the UKRI’s EPSRC Project Cumulative Revelations in Personal Data (Grant Number: EP/R033897/1) for theirsupport. They would also like to thank David Losada for arranging this collaboration.

PY - 2021/9/14

Y1 - 2021/9/14

N2 - This paper briefly describes our research groups' efforts in tackling Task 1 (Early Detection of Signs of Self-Harm), and Task 2 (Measuring the Severity of the Signs of Depression) from the CLEF eRisk Track. Core to how we approached these problems was the use of BERT-based classifiers which were trained specifically for each task. Our results on both tasks indicate that this approach delivers high performance across a series of measures, particularly for Task 1, where our submissions obtained the best performance for precision, F1, latency-weighted F1 and ERDE at 5 and 50. This work suggests that BERT-based classifiers, when trained appropriately, can accurately infer which social media users are at risk of self-harming, with precision up to 91.3% for Task 1. Given these promising results, it will be interesting to further refine the training regime, classifier and early detection scoring mechanism, as well as apply the same approach to other related tasks (e.g., anorexia, depression, suicide).

AB - This paper briefly describes our research groups' efforts in tackling Task 1 (Early Detection of Signs of Self-Harm), and Task 2 (Measuring the Severity of the Signs of Depression) from the CLEF eRisk Track. Core to how we approached these problems was the use of BERT-based classifiers which were trained specifically for each task. Our results on both tasks indicate that this approach delivers high performance across a series of measures, particularly for Task 1, where our submissions obtained the best performance for precision, F1, latency-weighted F1 and ERDE at 5 and 50. This work suggests that BERT-based classifiers, when trained appropriately, can accurately infer which social media users are at risk of self-harming, with precision up to 91.3% for Task 1. Given these promising results, it will be interesting to further refine the training regime, classifier and early detection scoring mechanism, as well as apply the same approach to other related tasks (e.g., anorexia, depression, suicide).

KW - Self-harm

KW - Depression

KW - Classification

KW - Social media

KW - Early detection

KW - BERT

KW - XLM-RoBERTa

UR - https://link.springer.com/chapter/10.1007/978-3-030-85251-1_15

UR - https://pureportal.strath.ac.uk/en/publications/f57eb753-d43a-4670-9a90-2cbed04df588

U2 - 10.1007/978-3-030-85251-1_15

DO - 10.1007/978-3-030-85251-1_15

M3 - Conference publication

SN - 9783030852504

T3 - Lecture Notes in Computer Science

SP - 189

EP - 200

BT - Experimental IR Meets Multilinguality, Multimodality, and Interaction

A2 - Candan, K. Selçuk

A2 - Ionescu, Bogdan

A2 - Goeuriot, Lorraine

A2 - Larsen, Birger

A2 - Mueller, Henning

A2 - Joly, Alexis

A2 - Maistro, Maria

A2 - Piroi, Florina

A2 - Faggioli, Guglielmo

A2 - Ferro, Nicolo

T2 - 12th International Conference of the CLEF Association

Y2 - 21 September 2021 through 24 September 2021

ER -

Martínez-Castaño R, Htait A, Azzopardi L, Moshfeghi Y. BERT-Based Transformers for Early Detection of Mental Health Illnesses. In Candan KS, Ionescu B, Goeuriot L, Larsen B, Mueller H, Joly A, Maistro M, Piroi F, Faggioli G, Ferro N, editors, Experimental IR Meets Multilinguality, Multimodality, and Interaction: 12th International Conference of the CLEF Association, CLEF 2021, Virtual Event, September 21–24, 2021, Proceedings. 2021. p. 189-200. (Lecture Notes in Computer Science). Epub 2021 Aug 24. doi: 10.1007/978-3-030-85251-1_15

BERT-Based Transformers for Early Detection of Mental Health Illnesses

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this