City Research Online

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

Export

Downloads