no code implementations • NAACL (CLPsych) 2021 • Kasia Hitczenko, Henry Cowan, Vijay Mittal, Matthew Goldrick
While we find group differences between at-risk and healthy control populations, we also find that the measures mostly do not correlate with existing measures of thought disorder symptoms (what they are intended to measure), but rather correlate with surface properties of the speech (e. g., sentence length) and sociodemographic properties of the speaker (e. g., race).
1 code implementation • 29 Jun 2022 • Yael Segal, Kasia Hitczenko, Matthew Goldrick, Adam Buchwald, Angela Roberts, Joseph Keshet
These segmentations predicted by the models are used to obtain measures of speech rate and sound duration.