Using Language Processing and Speech Analysis for the Identification of Psychosis and Other Disorders

Abstract

Increasingly, data-driven methods have been implemented to understand psychopathology. Language is the main source of information in psychiatry and represents "big data" at the level of the individual. Language and behavior are amenable to computational natural language processing (NLP) analytics, which may help operationalize the mental status examination. In this review, we highlight the application of NLP to schizophrenia and its risk states as an exemplar of its use, operationalizing tangential and concrete speech as reductions in semantic coherence and syntactic complexity, respectively. Other clinical applications are reviewed, including forecasting suicide risk and detecting intoxication. Challenges and future directions are discussed, including biomarker development, harmonization, and application of NLP more broadly to behavior, including intonation/prosody, facial expression and gesture, and the integration of these in dyads and during discourse. Similar NLP analytics can also be applied beyond humans to behavioral motifs across species, important for modeling psychopathology in animal models. Finally, clinical neuroscience can inform the development of artificial intelligence.

Keywords: Language; Schizophrenia; Semantics; Speech graphs; Suicidal; Syntax.

Figure 1

Semantic similarity of words in text and word embeddings representation A passage from Paradise Lost analyzed with LSA to demonstrate how content and proximity are related. Left panel: words in blue and red were selected to highlight ideas of order and pleasure, respectively; moreover, they appear contiguous in the text. Right panel: 2D projection of LSA vectors showing how the words cluster according to their meaning.

Figure 2

A) Part-of-speech tagging B) Word graph representation Figure 2A: part-of-speech (POS) tagging. The decomposition of the sentence “I think, therefore I am” into POS also generates a phrase tree structure (Noun Phrase, Verb Phrase, etc.) whose depth and diversity (POS/length) can be used as measures of complexity. Figure 2B: Graph representation. The directed graph identifies a recurrence to the word “I”.