Disfluencies as extra-propositional indicators of cognitive processing

  • Authors:
  • Kathryn Womack;Wilson McCoy;Cecilia Ovesdotter Alm;Cara Calvelli;Jeff B. Pelz;Pengcheng Shi;Anne Haake

  • Affiliations:
  • Rochester Institute of Technology;Rochester Institute of Technology;Rochester Institute of Technology;Rochester Institute of Technology;Rochester Institute of Technology;Rochester Institute of Technology;Rochester Institute of Technology

  • Venue:
  • ExProM '12 Proceedings of the Workshop on Extra-Propositional Aspects of Meaning in Computational Linguistics
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

We explore filled pause usage in spontaneous medical narration. Expert physicians viewed images of dermatological conditions and provided a description while working toward a diagnosis. The narratives were analyzed for differences in filled pauses used by attending (experienced) and resident (in-training) physicians and by male and female physicians. Attending physicians described more and used more filled pauses than residents. No difference was found by speaker gender. Acoustic speech features were examined for two types of filled pauses: nasal (e.g. um) and non-nasal (e.g. uh). Nasal filled pauses were more often followed by longer silent pauses. Scores capturing diagnostic correctness and diagnostic thoroughness for each narrative were compared against filled pauses. The number of filled and silent pauses trends upward as correctness scores increase, indicating a tentative relationship between filled pause usage and expertise. Also, we report on a computational model for predicting types of filled pause.