City Research Online

Linguistic Indicators of Severity and Progress in Online Text-based Therapy for Depression

Howes, C., Purver, M. & McCabe, R. ORCID: 0000-0003-2041-7383 (2014). Linguistic Indicators of Severity and Progress in Online Text-based Therapy for Depression. Paper presented at the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 27 June 2014, Baltimore Maryland, USA. doi: 10.3115/v1/w14-3202

Abstract

Mental illnesses such as depression andanxiety are highly prevalent, and therapyis increasingly being offered online. Thisnew setting is a departure from face-to-face therapy, and offers both a challengeand an opportunity – it is not yet knownwhat features or approaches are likely tolead to successful outcomes in such a dif-ferent medium, but online text-based ther-apy provides large amounts of data for lin-guistic analysis. We present an initial in-vestigation into the application of compu-tational linguistic techniques, such as topicand sentiment modelling, to online ther-apy for depression and anxiety. We findthat important measures such as symptomseverity can be predicted with compara-ble accuracy to face-to-face data, usinggeneral features such as discussion topicand sentiment; however, measures of pa-tient progress are captured only by finer-grained lexical features, suggesting thataspects of style or dialogue structure mayalso be important.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: Published in Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality Baltimore, Maryland, USA: ASsociation for Computational Linguistics. pp. 7-16. https://www.aclweb.org/anthology/W14-3202. doi: 10.3115/v1/W14-3202
Subjects: B Philosophy. Psychology. Religion > BF Psychology
P Language and Literature > P Philology. Linguistics
Departments: School of Health & Psychological Sciences > Healthcare Services Research & Management
[img]
Preview
Text - Published Version
Available under License Creative Commons: Attribution-Noncommercial-Share Alike 3.0.

Download (141kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login