Detecting formal thought disorder by deep contextualized word representations

•NLP algorithm can detect features of formal thought disorder (FTD).•Deep contextual word representations may be used to improve detection of the FTD.•NLP accuracy is comparable to observer’s ratings. Computational linguistics has enabled the introduction of objective tools that measure some of the...

Full description

Bibliographic Details

Published in:	Psychiatry research Vol. 304; p. 114135
Main Authors:	Sarzynska-Wawer, Justyna, Wawer, Aleksander, Pawlak, Aleksandra, Szymanowska, Julia, Stefaniak, Izabela, Jarkiewicz, Michal, Okruszek, Lukasz
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.10.2021
Subjects:	Deep learning Language Natural language processing Schizophrenia Deep learning Schizophrenia Natural language processing Language
ISSN:	0165-1781, 1872-7123, 1872-7123
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!