Aiding usability evaluation via detection of excessive visual search

  • Authors:
  • Oleg Komogortsev;Corey Holland;Dan Tamir;Carl Mueller

  • Affiliations:
  • Texas State University-San Marcos, San Marcos, TX, USA;Texas State University-San Marcos, San Marcos, TX, USA;Texas State University-San Marcos, San Marcos, TX, USA;Texas State University-San Marcos, San Marcos, TX, USA

  • Venue:
  • CHI '11 Extended Abstracts on Human Factors in Computing Systems
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents an objective evaluation of several methods for the automated classification of excessive visual search, a technique which has the potential to aid in the identification of usability problems during software usability testing. Excessive visual search was identified by a number of eye movement metrics, including: fixation count, saccade amplitude, convex hull area, scanpath inflections, scanpath length, and scanpath duration. The excessive search intervals identified by each algorithm were compared to those produced by manual classification. The results indicate that automated classification can be successfully employed to substantially reduce the amount of recorded data reviewed during usability testing, with relatively little loss in accuracy.