Improving predictions of polite and frustrated speech using linguistic features associated with different cognitive states in children
- Cindy Chiang, University of Southern California, Los Angeles , California, United States
- Jacqueline Brixey, USC Institute for Creative Technologies, Los Angeles, California, United States
- James Gibson, University of Southern California, Los Angeles, California, United States
- Morteza Dehghani,
AbstractChildrens poor emotional self-regulation is associated with poor mental health outcomes. This study presents methods that improve prediction rates of polite and frustrated speech using linguistic cues. These improvements can be used to help auto- matically identify characteristics of poor self-regulation in fu- ture studies. This work adds to previous research by consider- ing existing computer science, psychology, and psycholinguis- tics methodologies and findings. More specifically, features associated with childrens cognitive control capacities across age groups are considered to investigate acoustic, semantic, and syntactic features in speech. The current analyses indi- cate that the features most predictive for polite and frustrated speech differ, a combination of features work best for predict- ing both speech types, and the predictive quality of features do not vary substantially by age. Further work should be con- ducted to clarify how well these findings transfer to general and clinical populations as well as to consider the developmental norms of different age groups.
Return to previous page