An evaluation of Dasher with a high-performance language model as a gaze communication method

Daniel Rough, Keith Vertanen, Per Ola Kristensson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Dasher is a promising fast assistive gaze communication method. However, previous evaluations of Dasher have been inconclusive. Either the studies have been too short, involved too few participants, suffered from sampling bias, lacked a control condition, used an inappropriate language model, or a combination of the above. To rectify this, we report results from two new evaluations of Dasher carried out using a Tobii P10 assistive eye-tracker machine. We also present a method of modifying Dasher so that it can use a state-of-the-art long-span statistical language model. Our experimental results show that compared to a baseline eye-typing method, Dasher resulted in significantly faster entry rates (12.6 wpm versus 6.0 wpm in Experiment 1, and 14.2 wpm versus 7.0 wpm in Experiment 2). These faster entry rates were possible while maintaining error rates comparable to the baseline eye-typing method. Participants' perceived physical demand, mental demand, effort and frustration were all significantly lower for Dasher. Finally, participants significantly rated Dasher as being more likeable, requiring less concentration and being more fun.

Original languageEnglish
Title of host publicationAVI '14
Subtitle of host publicationProceedings of the 2014 International Working Conference on Advanced Visual Interfaces
PublisherAssociation for Computing Machinery (ACM)
Pages169-176
Number of pages8
ISBN (Electronic)9781450327756
DOIs
Publication statusPublished - May 2014
Event2014 12th International Working Conference on Advanced Visual Interfaces, AVI 2014 - Como, Italy
Duration: 27 May 201430 May 2014

Conference

Conference2014 12th International Working Conference on Advanced Visual Interfaces, AVI 2014
CountryItaly
CityComo
Period27/05/1430/05/14

Keywords

  • assistive gaze communication
  • Dasher
  • eye-typing

Fingerprint Dive into the research topics of 'An evaluation of Dasher with a high-performance language model as a gaze communication method'. Together they form a unique fingerprint.

Cite this