Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Towards preemptive detection of depression and anxiety in Twitter

Owen, David ORCID: https://orcid.org/0000-0002-4028-0591, Camacho Collados, Jose ORCID: https://orcid.org/0000-0003-1618-7239 and Espinosa-Anke, Luis ORCID: https://orcid.org/0000-0001-6830-9176 2020. Towards preemptive detection of depression and anxiety in Twitter. Presented at: Social Media Mining for Health Applications Workshop & Shared Task 2020, Barcelona, Spain, 8-13 December 2020. Published in: Gonzalez-Hernandez, Graciela, Klein, Ari Z., Flores, Ivan, Weissenbacher, Davy, Magge, Arjun, O'Connor, Karen, Sarker, Abeed, Minard, Anne-Lyse, Tutubalina, Elena, Miftahutdinov, Zulfat and Alimova, Ilseyar eds. Proceedings of the Fifth Social Media Mining for Health Applications Workshop & Shared Task. Association for Computational Linguistics, pp. 82-89.

[thumbnail of 2020.smm4h-1.12.pdf]
Preview
PDF - Published Version
Available under License Creative Commons Attribution.

Download (144kB) | Preview

Abstract

Depression and anxiety are psychiatric disorders that are observed in many areas of everyday life. For example, these disorders manifest themselves somewhat frequently in texts written by nondiagnosed users in social media. However, detecting users with these conditions is not a straightforward task as they may not explicitly talk about their mental state, and if they do, contextual cues such as immediacy must be taken into account. When available, linguistic flags pointing to probable anxiety or depression could be used by medical experts to write better guidelines and treatments. In this paper, we develop a dataset designed to foster research in depression and anxiety detection in Twitter, framing the detection task as a binary tweet classification problem. We then apply state-of-the-art classification models to this dataset, providing a competitive set of baselines alongside qualitative error analysis. Our results show that language models perform reasonably well, and better than more traditional baselines. Nonetheless, there is clear room for improvement, particularly with unbalanced training sets and in cases where seemingly obvious linguistic cues (keywords) are used counter-intuitively.

Item Type: Conference or Workshop Item (Paper)
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Publisher: Association for Computational Linguistics
Date of First Compliant Deposit: 12 October 2020
Date of Acceptance: 1 September 2020
Last Modified: 28 Nov 2024 11:54
URI: https://orca.cardiff.ac.uk/id/eprint/135512

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics