A Computational Approach to Analyzing Disrupted Language in Schizophrenia: Integrating Surprisal and Coherence Measures

2025-11-05

AI Summary

This study aims to quantify language disturbances in schizophrenia and examine their association with clinical symptom severity. Method: For the first time, we jointly modeled language abnormalities in natural speech using two computational linguistic metrics—sentence-level surprisal and discourse-level semantic coherence—and correlated these metrics with standardized clinical scale scores via correlation and discriminative analyses. Contribution/Results: Both metrics significantly differentiated patients from healthy controls (p < 0.001). Elevated surprisal and reduced semantic coherence showed robust correlations with positive symptom severity—particularly formal thought disorder—with absolute correlation coefficients exceeding 0.45. This dual-dimensional computational characterization provides an interpretable, reproducible, and dynamically grounded cognitive marker of language dysfunction in schizophrenia, demonstrating strong potential as an objective, quantitative biomarker for clinical and research applications.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Computer Vision: Language and Vision

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Social Networks and Social Media: Computational social science

Abstract

Language disruptions are one of the well-known effects of schizophrenia symptoms. They are often manifested as disorganized speech and impaired discourse coherence. These abnormalities in spontaneous language production reflect underlying cognitive disturbances and have the potential to serve as objective markers for symptom severity and diagnosis of schizophrenia. This study focuses on how these language disruptions can be characterized in terms of two computational linguistic measures: surprisal and semantic coherence. By computing surprisal and semantic coherence of language using computational models, this study investigates how they differ between subjects with schizophrenia and healthy controls. Furthermore, this study provides further insight into how language disruptions in terms of these linguistic measures change with varying degrees of schizophrenia symptom severity.

Problem

• Analyzing language disruptions in schizophrenia using computational measures
• Comparing surprisal and coherence between patients and healthy controls
• Investigating how language abnormalities correlate with symptom severity

Innovation

• Using surprisal measures to analyze language disruptions
• Applying semantic coherence for schizophrenia assessment
• Integrating computational models for symptom severity tracking