Predicting psychosis and schizophrenia using language patterns, with Neguine Rezaii

This is a reshare of a 2020 talk with psychology researcher Neguine Rezaii. She and her research team used machine learning to find language patterns used by teenagers who were at risk of schizophrenia that were correlated with later schizophrenia diagnosis. The two language patterns found in the subjects' speech were 1) a low semantic density (i.e., low degree of meaning), and 2) speech related to sound or voices.