logo
ResearchBunny Logo
Multimodal assessment of communicative-pragmatic features in schizophrenia: a machine learning approach

Psychology

Multimodal assessment of communicative-pragmatic features in schizophrenia: a machine learning approach

A. Parola, I. Gabbatore, et al.

This study, conducted by Alberto Parola, Ilaria Gabbatore, Laura Berardinelli, Rogerio Salvini, and Francesca M. Bosco, unveils groundbreaking insights into the communicative differences between individuals with schizophrenia and healthy controls. Utilizing a multimodal assessment coupled with machine learning, the research reveals linguistic irony as a pivotal indicator, boasting an impressive 82% accuracy in participant classification. Discover how these findings could reshape pragmatic theory and clinical assessments.

00:00
00:00
Playback language: English
Abstract
This paper investigates the communicative-pragmatic features that best discriminate between individuals with schizophrenia and healthy controls using a multimodal assessment and a machine learning approach. A Decision Tree model achieved 82% accuracy, 76% sensitivity, and 91% precision in classifying participants. Linguistic irony emerged as the most significant feature, followed by violations of Gricean maxims and extralinguistic deceitful/sincere acts. The findings are discussed in relation to pragmatic theory and their clinical implications for assessment and rehabilitation.
Publisher
npj Schizophrenia
Published On
May 24, 2021
Authors
Alberto Parola, Ilaria Gabbatore, Laura Berardinelli, Rogerio Salvini, Francesca M. Bosco
Tags
schizophrenia
machine learning
communicative features
pragmatics
linguistic irony
Gricean maxims
clinical implications
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny