Parameter Selection for Analyzing Conversations with Autism Spectrum Disorder

TL;DR

This study tackles ASD diagnosis by analyzing conversational interactions in the ADOS-2 assessment, leveraging a rich set of acoustic-prosodic and linguistic features extracted from child and psychologist turns across multiple tasks. The authors combine openSMILE-based acoustic features with LIWC and lexical language measures, then apply correlation-based feature selection and random-forest classification to identify a minimal yet informative feature subset and to explore cross-context generalization. Key findings show that language features, especially when combined with acoustic cues and task context, improve diagnostic accuracy, with substantial feature reduction achievable without loss of performance; psychologist-turn features also hold predictive value. The work suggests AI-assisted, context-aware analysis can augment clinician workflows for ASD diagnosis, while highlighting the need for cautious deployment and future multimodal extension, manual diarization improvements, and cross-practitioner validation.

Abstract

The diagnosis of autism spectrum disorder (ASD) is a complex, challenging task as it depends on the analysis of interactional behaviors by psychologists rather than the use of biochemical diagnostics. In this paper, we present a modeling approach to ASD diagnosis by analyzing acoustic/prosodic and linguistic features extracted from diagnostic conversations between a psychologist and children who either are typically developing (TD) or have ASD. We compare the contributions of different features across a range of conversation tasks. We focus on finding a minimal set of parameters that characterize conversational behaviors of children with ASD. Because ASD is diagnosed through conversational interaction, in addition to analyzing the behavior of the children, we also investigate whether the psychologist's conversational behaviors vary across diagnostic groups. Our results can facilitate fine-grained analysis of conversation data for children with ASD to support diagnosis and intervention.