Year: 2024
Type: conference-paper
Abstract: Psycholinguistic literature shows that Post-Traumatic Stress Disorder (PTSD) and its specific criteria as stated inthe DSM-5 affect language. We aim to analyze these effects using automated methods while keepinginterpretability, to quantify them and their importance. However, automatic PTSD detection is an open problem,with NLP-based approaches being even rarer. With psychiatrists often having interviews with the patient, theproblem itself of detecting PTSD from a single discourse without interaction is a complex one and gold standardtests have only 80% accuracy in doing so. In this study, we propose an approach, focusing on speechdisorganization effects only and their association with PTSD. Our method, based on sentence similarity, used state-of-the-art models to underline speech organization in transcribed discourse. Using such representation allowed usto create features inferred from the way psychiatrists read texts. On the 13-November Cohorts, our method reachedaccuracy comparable to human standards for our dataset, both in PTSD prediction and Criterion D (negativealterations in cognitions and mood) detection. According to the literature, criterion D is the most related to speechorganization. We also added a second contribution to our work: a method extracting parts of texts that contain thespeech disorder phenomenon.
Source: HAL
Language: English
Topic: Mental Health via Writing
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4400140574
