# Semantic Characteristics of Schizophrenic Speech

## TL;DR

This study uses NLP tools to analyze speech patterns of Hebrew-speaking schizophrenia inpatients, identifying differences in cohesion and word usage that could aid automatic diagnosis.

## Contribution

It introduces a novel NLP-based approach to detect schizophrenia through analysis of speech cohesion and descriptive word usage in Hebrew.

## Key findings

- Controls maintain more cohesive speech than inpatients.
- Inpatients and controls differ in their use of adjectives and adverbs.
- Speech patterns can potentially be used for automatic schizophrenia detection.

## Abstract

Natural language processing tools are used to automatically detect disturbances in transcribed speech of schizophrenia inpatients who speak Hebrew. We measure topic mutation over time and show that controls maintain more cohesive speech than inpatients. We also examine differences in how inpatients and controls use adjectives and adverbs to describe content words and show that the ones used by controls are more common than the those of inpatients. We provide experimental results and show their potential for automatically detecting schizophrenia in patients by means only of their speech patterns.