A3: HCI coding guideline for research using video annotation to assess behavior of nonverbal subjects with computer-based intervention

Joshua Hailpern, Karrie Karahalios, James Halle, Laura Segebart DeThorne, Mary Kelsey Coletto

Research output: Contribution to journalArticle

Abstract

HCI studies assessing nonverbal individuals (especially those who do not communicate through traditional linguistic means: spoken, written, or sign) are a daunting undertaking. Without the use of directed tasks, interviews, questionnaires, or question-answer sessions, researchers must rely fully upon observation of behavior, and the categorization and quantification of the participant's actions. This problem is compounded further by the lack of metrics to quantify the behavior of nonverbal subjects in computer-based intervention contexts. We present a set of dependent variables called A3 (pronounced A-Cubed) or Annotation for ASD Analysis, to assess the behavior of this demographic of users, specifically focusing on engagement and vocalization. This paper demonstrates how theory from multiple disciplines can be brought together to create a set of dependent variables, as well as demonstration of these variables, in an experimental context. Through an examination of the existing literature, and a detailed analysis of the current state of computer vision and speech detection, we present how computer automation may be integrated with the A3 guidelines to reduce coding time and potentially increase accuracy. We conclude by presenting how and where these variables can be used in multiple research areas and with varied target populations.

Original languageEnglish (US)
Article number8
JournalACM Transactions on Accessible Computing
Volume2
Issue number2
DOIs
StatePublished - Jun 1 2009

    Fingerprint

Keywords

  • ASD
  • Annotation
  • Audio feedback
  • Autism
  • Coding
  • Guideline
  • Intervention
  • Kappa
  • Nonverbal
  • Point-by-point agreement
  • Reliability
  • Video
  • Visualization

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Science Applications

Cite this