Predictive Linguistic Features of Schizophrenia

Abstract

Schizophrenia is one of the most disabling and difficult to treat of all human medical/health conditions, ranking in the top ten causes of disability worldwide. It has been a puzzle in part due to difficulty in identifying its basic, fundamental components. Several studies have shown that some manifestations of schizophrenia (e.g., the negative symptoms that include blunting of speech prosody, as well as the disorganization symptoms that lead to disordered language) can be understood from the perspective of linguistics. However, schizophrenia research has not kept pace with technologies in computational linguistics, especially in semantics and pragmatics. As such, we examine the writings of schizophrenia patients analyzing their syntax, semantics and pragmatics. In addition, we analyze tweets of (self proclaimed) schizophrenia patients who publicly discuss their diagnoses. For writing samples dataset, syntactic features are found to be the most successful in classification whereas for the less structured Twitter dataset, a combination of features performed the best.

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

“…We obtain our best scores with the longest sequences (3-POS, 72.55% acc., 74.34% F 1 ). These scores are higher than the ones reported by Kayi et al (2017) on tweets (69.20% F 1 ) or essays (69.76% F 1 ) with simple POS tags and a lot more documents, and are very close to Allende-Cid et al ( 2019) with meta-POS (75.1% in F 1 ): this confirms the predictive power of POS for the task.…”

“…More recent approaches considered syntactic, semantic, and sentiment information (Kayi et al, 2017;Allende-Cid et al, 2019). Both studies show good performance with morpho-syntactic features, especially with Part-Of-Speech (POS) tags.…”

Do Models of Mental Health Based on Social Media Data Generalize?

“…In the last decade, there has been substantial growth in the area of digital psychiatry. Automated methods using natural language processing have been able to detect mental health disorders based on a person's language in a variety of data types, such as social media (Mowery et al, 2016;Morales et al, 2017), speech (Iter et al, 2018) and other writings (Kayi et al, 2017;Just et al, 2019). As in-person clinical visits are made increasingly difficult by socioeconomic barriers and public-health crises, such as COVID-19, tools for measuring mental wellness using implicit signal become more important than ever (Abdel-Rahman, 2019;Bojdani et al, 2020).…”

Facial and vocal markers of schizophrenia measured using remote smartphone assessments

“…Analysis of vocal markers included those that have previously demonstrated effects in studies of individuals with schizophrenia (Alberto et al, 2019; Martínez-Sánchez et al, 2015). These properties, recorded both during free speech and evoked vocal expressions, include loudness of the individual’s voice in Decibels ( vocal intensity ), average fundamental frequency in Hertz ( fundamental frequency mean ), standard deviation of fundamental frequency ( fundamental frequency stdev ), jitter ( vocal jitter ), harmonics-to-noise ratio ( harmonics to noise ratio ) and the percentage of time with detected speech in an audio file ( speech prevalence) (Cannizzaro et al, 2005; Covington et al, 2012; Kliper et al, 2019; Sarioglu Kayi et al, 2017; Saxman & Burk, 1968).…”

“…fundamental frequency mean and stdev, jitter, harmonics-to-noise ratio ) while also measuring speech characteristics such as amount of time spoken (i.e. speech prevalence ) (Cannizzaro et al, 2005; Covington et al, 2012; Kliper et al, 2019; Sarioglu Kayi et al, 2017; Saxman & Burk, 1968). A large number of variables can be calculated from video and audio data sources; however, the analyses presented herein were limited to features that have evidence and a theoretical basis for relationship to schizophrenia severity and symptoms in the scientific literature.…”