Systemic Functional Linguistics in the Digital Age - Sheena Gardner

Systemic Functional Linguistics in the Digital Age - Sheena Gardner

Chapter 20: Linguistic Characteristics of Schizophrenia and Mania Computationally Revealed

Systemic Functional Linguistics in the Digital Age - Sheena Gardner

Ekaterina Shagalov [+-]
Dixilang Company
Ekaterina Shagalov holds a PhD degree from Bar-Ilan University. In her doctoral study, she used computational means to distinguish mania and schizophrenia on the basis of linguistic characteristics that coincide with clinical descriptions of the disorders. She works as a linguist in Dixilang Company which has developed speech recognition technology.
Jonathan Fine† [+-]
Bar-Ilan University
Jonathan Fine, who died in September 2015, taught in the department of English at Bar-Ilan University. He published studies on the language of psychiatric syndromes including pervasive developmental disorders, schizophrenia, and attention-deficit-hyperactivity disorder. His other research includes discourse analysis, systemic functional theory, first and second language acquisition and genre. He edited or authored five books on language in use including Language in Psychiatry: A Handbook of Clinical Practice (Equinox).

Description

The clinical interview is commonly used in psychiatry for diagnosis, though it is time-consuming, needs special training, and multiple sources of information. Recently computerized analysis of speech offers objective means for evaluating symptoms in schizophrenia. Cohen writes: "Accurate measurement of negative symptoms is crucial for understanding and treating schizophrenia. However, current measurement strategies are reliant on subjective symptom rating scales, which often have psychometric and practical limitations. Computerized analysis of patients’ speech offers a sophisticated and objective means of evaluating negative symptoms" (2007: 827). Specific to schizophrenia, machine learning techniques have been used in the study of patients’ writings (Strous et al. 2008). With large within group differences, there is no one language characteristic that distinguishes speakers with schizophrenia and mania. However, this study has found that combinations of features and possible correlations among the features separated the diagnostic groups, characterizing the disorders. Transcripts of subjects with schizophrenia (six transcripts) and mania (four transcripts) were digitalized to compose two sub-corpora. The texts were annotated and analyzed (UAM Corpus Tool, O’Donnell 2008) for syntactic complexity, amount of talk, dysfluencies, type-token ratio, lexical similarity, and word frequency among other variables.

Notify A Colleague

Citation

Shagalov, Ekaterina; Fine, Jonathan . Chapter 20: Linguistic Characteristics of Schizophrenia and Mania Computationally Revealed. Systemic Functional Linguistics in the Digital Age. Equinox eBooks Publishing, United Kingdom. p. 328-347 Nov 2016. ISBN 9781781792384. https://www.equinoxpub.com/home/view-chapter/?id=26124. Date accessed: 12 Dec 2018 doi: 10.1558/equinox.26124. Nov 2016

Dublin Core Metadata