Multidimensional Pareto optimization of touchscreen keyboards for speed, familiarity and improved spell checking

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

52 Citations (Scopus)
188 Downloads (Pure)


The paper presents a new optimization technique for keyboard layouts based on Pareto front optimization. We used this multifactorial technique to create two new touchscreen phone keyboard layouts based on three design metrics: minimizing finger travel distance in order to maximize text entry speed, a new metric to maximize the quality of spell correction quality by minimizing neighbouring key ambiguity, and maximizing familiarity through a similarity function with the standard Qwerty layout. The paper describes the optimization process and resulting layouts for a standard trapezoid shaped keyboard and a more rectangular layout. Fitts' law modelling shows a predicted 11% improvement in entry speed without taking into account the significantly improved error correction potential and the subsequent effect on speed. In initial user tests typing speed dropped from approx. 21wpm with Qwerty to 13wpm (64%) on first use of our layout but recovered to 18wpm (85%) within four short trial sessions, and was still improving. NASA TLX forms showed no significant difference on load between Qwerty and our new layout use in the fourth session. Together we believe this shows the new layouts are faster and can be quickly adopted by users.
Original languageEnglish
Title of host publicationProceedings of the SIGCHI Conference on Human Factors in Computing Systems
Place of PublicationNew York
Number of pages10
Publication statusPublished - May 2012
EventACM CHI - Vancouver, Canada
Duration: 31 Mar 201131 Mar 2011


ConferenceACM CHI


  • Pareto optimization
  • touchscreen keyboards
  • spell checking


Dive into the research topics of 'Multidimensional Pareto optimization of touchscreen keyboards for speed, familiarity and improved spell checking'. Together they form a unique fingerprint.

Cite this