Ph.D. Defense of Dissertation: James Clawson

Add to Calendar
Date:
October 30, 2012 1:00 pm - 4:00 pm
Location:
TSRB 134

Title: On-the-Go Text Entry: Evaluating and Improving Mobile Text Input on mini-QWERTY Keyboards

James Clawson
Human-Centered Computing
School of Interactive Computing
College of Computing
Georgia Institute of Technology

Date: Tuesday, October 30, 2012
Time: 1:00-4:00pm
Location: TSRB 134

Committee:

  • Dr. Thad Starner, School of Interactive Computing, Advisor
  • Dr. Gregory Abowd, School of Interactive Computing
  • Dr. Beth Mynatt, School of Interactive Computing
  • Dr. Scott MacKenzie, Department of Computer Science and Engineering, York University
  • Dr. Jacob Wobbrock, Information School, University of Washington

 

Abstract:
To date, hundreds of millions of mini-QWERTY keyboard equipped devices (miniaturized versions of a full desktop keyboard)  have been sold. Accordingly, a large percentage of text messages originate from fixed-key, mini-QWERTY keyboard enabled mobile phones. In this dissertation, I present ways to improve text messaging on mini-QWERTY keyboard enabled mobile phones through the use of an automatic error correction algorithm. Over a series of three longitudinal studies I quantify how quickly and accurately individuals can input text on mini-QWERTY keyboards. I evaluate performance in ideal laboratory conditions as well as in a variety of mobile contexts. My first study establishes baseline performance measures; my second study investigates the impact of limited visibility on text input performance; and my third study investigates the impact of mobility (sitting, standing, and walking) on text input performance. After approximately five hours of practice, participants achieved expertise typing almost 60 words-per-minute at almost 95% accuracy. Upon completion of these studies, I examine the types of errors that people make when typing on mini-QWERTY keyboards. Having discovered a common pattern in errors, I develop and refine an algorithm to automatically detect and correct errors in mini-QWERTY keyboard enabled text input. I both validate the algorithm through the analysis of pre-recorded typing data and then empirically evaluate the impacts of automatic error correction on live mini-QWERTY keyboard text input. Validating the algorithm over various datasets, I demonstrate the potential to correct approximately a 25% of the total errors and correct up to 3% of the total keystrokes. Evaluating automatic error detection and correction on live typing results in successfully correcting 60.80% of the off-by-one errors committed by participants while increasing typing rates by almost 2 words-per-minute without introducing any distraction.