Differences in syntactic and semantic analysis based on machine learning algorithms in prodromal psychosis and normal adolescents

Khamelia Malik, I. Gusti Agung Ayu Widyarini, Fransiska Kaligis, A. A.A.A. Kusumawardhani, Prasandhya Astagiri Yusuf, Adila Alfa Krisnadhi, Oskar Riandi, Arierta Pujitresnani

Research output: Contribution to journalArticlepeer-review

Abstract

Schizophrenia has the main symptom of psychosis which is characterized by speech incoherence due to thought process disturbance. Before schizophrenia, there is a prodromal phase of psychosis in adolescence. Early recognition of this phase is important to prevent the development of symptoms into a severe mental disorder. Machine learning technology can be used to predict thought process disturbance through syntactic and semantic analysis of speech. This study aims to describe the differences in syntactic and semantic analysis in prodromal psychosis and normal adolescents. The research subjects consisted of 70 adolescents aged 14–19 years which were divided into 2 groups. Based on the results of the Prodromal Questionnaire-Brief (PQ-B) Indonesian version, the subjects were split into two groups: prodromal and normal. All participants were voice-recorded during interviews using an open-ended qualitative questionnaire. Syntactic and semantic analysis was carried out on all data which amounted to 1017 phrase segments and classified by machine learning. This is the first study in Indonesia to compare the analysis of syntactic and semantic aspects in prodromal psychosis and normal adolescent populations. There were significant differences in syntactic and semantic analysis between groups of adolescents with prodromal psychosis and normal adolescents at the minimum value of coherence and frequency of use of nouns, personal pronouns, subordinate conjunctions, adjectives, prepositions, and proper nouns.

Original languageEnglish
Article number103633
JournalAsian Journal of Psychiatry
Volume85
DOIs
Publication statusPublished - Jul 2023

Keywords

  • Machine learning
  • Prodromal
  • Psychosis
  • Semantics
  • Syntax

Fingerprint

Dive into the research topics of 'Differences in syntactic and semantic analysis based on machine learning algorithms in prodromal psychosis and normal adolescents'. Together they form a unique fingerprint.

Cite this