Early risk detection of self-harm and depression severity using BERT-based transformers: iLab at CLEF eRisk 2020

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

Research output: Chapter in Book/Published conference outputConference 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 languageEnglish
Title of host publicationWorking Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum
PublisherCEUR-WS.org
Number of pages16
Volume2696
Publication statusPublished - 25 Sep 2020
EventEarly Risk Prediction on the Internet: CLEF Workshop - Thessaloniki, Greece
Duration: 22 Sep 202025 Sep 2020
https://early.irlab.org/2020/index.html

Publication series

NameCEUR Workshop Proceedings
Volume2696
ISSN (Electronic)1613-0073

Workshop

WorkshopEarly Risk Prediction on the Internet: CLEF Workshop
Abbreviated titleERISK 2020
Country/TerritoryGreece
CityThessaloniki
Period22/09/2025/09/20
Internet address

Bibliographical note

Copyright © 2020 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 bodies 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 Development Fund (ERDF) (accreditation 2019-2022 ED431G-2019/04, ED431C 2018/29, ED431C 2018/19). 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 their support. The authors would also like to thank David Losada for arranging this collaboration.

Keywords

  • Self-Harm
  • Depression
  • Classification
  • Social Media
  • Early Detection
  • BERT
  • XLM-RoBERTa

Fingerprint

Dive into the research topics of 'Early risk detection of self-harm and depression severity using BERT-based transformers: iLab at CLEF eRisk 2020'. Together they form a unique fingerprint.

Cite this