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

Chuyuan Li, Maxime Amblard, Chloé Braud, Caroline Demily, Nicolas Franck, Michel Musiol


Abstract
We investigate linguistic markers associated with schizophrenia in clinical conversations by detecting predictive features among French-speaking patients. Dealing with human-human 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%.
Anthology ID:
2021.codi-main.3
Volume:
Proceedings of the 2nd Workshop on Computational Approaches to Discourse
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic and Online
Venues:
CODI | CRAC | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
20–28
Language:
URL:
https://aclanthology.org/2021.codi-main.3
DOI:
10.18653/v1/2021.codi-main.3
Bibkey:
Cite (ACL):
Chuyuan Li, Maxime Amblard, Chloé Braud, Caroline Demily, Nicolas Franck, and Michel Musiol. 2021. Investigating non lexical markers of the language of schizophrenia in spontaneous conversations. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 20–28, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics.
Cite (Informal):
Investigating non lexical markers of the language of schizophrenia in spontaneous conversations (Li et al., CODI 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.codi-main.3.pdf
Code
 chuyuanli/non-lexical-markers-scz-conv