Degree Date


Document Type

Dissertation - Public Access

Degree Name

Psy.D. Doctor of Clinical Psychology

Academic Discipline

Clinical Psychology

First Advisor

Margaret S. Warner, PhD

Second Advisor

Emese Vitalis, PhD

Third Advisor

Jin Wu, PsyD


Though computational linguistic analyses have revealed the presence of distinctly characteristic language features in schizophrenic disordered speech, the relative stability of these language features in longitudinal samples is still unknown. This longitudinal pilot study analyzed schizophrenic disordered speech data from the archival therapy audio recordings of one patient spanning 23 years. End-to-end Neural Coreference Resolution software was used to analyze transcribed speech data from three therapy sessions to identify ambiguous pronouns, referred to as referential failures, which were reviewed and confirmed by multiple raters. Speech samples were analyzed using Google Cloud Natural Language API software for sentiment variables (i.e., score, valence, and magnitude). Referential failures and sentiment variables were analyzed within each session and all sessions combined to study the relationships between these variables within single sessions and over a span of 23 years. Results and implications for this study are discussed.