Investigating non lexical markers of the language of schizophrenia in spontaneous conversations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Investigating non lexical markers of the language of schizophrenia in spontaneous conversations

Abstract

We investigate linguistic markers associated with schizophrenia in clinical conversations by detecting predictive features among Frenchspeaking patients. Dealing with humanhuman dialogues makes for a realistic situation, but it calls for strategies to represent the context and face data sparsity. We compare different approaches for data representation-from individual speech turns to entire conversations-, and data modeling, using lexical, morphological, syntactic, and discourse features, dimensions presumed to be tightly connected to the language of schizophrenia. Previous English models were mostly lexical and reached high performance, here replicated (93.7% acc.). However, our analysis reveals that these models are heavily biased, which probably concerns most datasets on this task. Our new delexicalized models are more general and robust, with the best accuracy score at 77.9%.
Fichier principal
Vignette du fichier
codi2021_lisa (1).pdf (238.09 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03537698 , version 1 (21-01-2022)

Licence

Identifiers

Cite

Chuyuan Li, Maxime Amblard, Chloé Braud, Caroline Demily, Nicolas Franck, et al.. Investigating non lexical markers of the language of schizophrenia in spontaneous conversations. Proceedings of the 2nd Workshop on Computational Approaches to Discourse, Nov 2021, Punta Cana, Dominican Republic. pp.20--28, ⟨10.18653/v1/2021.codi-main.3⟩. ⟨hal-03537698⟩
131 View
163 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More