Speaker
Kamil Piwowar
(Goethe Universität)
Description
Large language models enable the quantification of speech as embeddings in a multidimensional semantic space. We collected interview data of an ADHD group (n = 74; 40 men and 34 women; mean age = 35.8 years) and healthy controls (n = 23; 14 men and 9 women; mean age = 33.6 years). By modelling consecutive utterances as semantic trajectories, we found that the ADHD group showed greater semantic jumpiness than healthy controls in an ANCOVA. These findings suggest reduced stability of semantic progression between adjacent utterances in ADHD.
Author
Kamil Piwowar
(Goethe Universität)