Deconstructing heterogeneity in schizophrenia through language: a semi-automated linguistic analysis and data-driven clustering approach

This study used a semi-automated multidimensional linguistic analysis combined with a machine-driven clustering technique to characterize the speech of 67 individuals with schizophrenia. Two subgroups with distinctive linguistic profiles were identified: one with higher fluency and lower lexical variety but greater use of psychological lexicon; the other with reduced fluency, greater lexical variety but reduced psychological lexicon. The former cluster was associated with lower symptoms and better quality of life, highlighting the importance of considering language disturbances in schizophrenia as multifaceted and approaching them in automated and data-driven ways.

Valentina Bambini, Federico Frau, Luca Bischetti, Federica Cuoco, Margherita Bechi, Mariachiara Buonocore, Giulia Agostoni, Ilaria Ferri, Jacopo Sapienza, Francesca Martini, Marco Spangaro, Giorgia Bigai, Federica Cocchi, Roberto Cavallaro, Marta Bosia