A committment to scientific excellence

Eatoni devotes a considerable fraction of its resources to research and development. Some of the results can be made public, and those will be presented here.

Additional whitepapers can be found at Documents.

Published WWRF 10	Risk Perception and the Discovery Period for Mobile Applications Howard Gutowitz and Terry Jones Why don't people use word-guessing text entry? Because it's too complex and unreliable. Published in the proceedings of the 10th World Wireless Research Forum (WWRF), October 2003, New York, New York	Published EACL 10	Barriers to Adoption of Dictionary-Based Text-Entry Methods: A Field Study Howard Gutowitz A field study comprising 230 man-in-the-street interviews shows that dictionary deficiencies are a principal reason that dictionary-based word-guessing text entry systems such as T9 are hard to learn as well as hard to use. Published in the proceedings of the 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL), April 2003, Budapest, Hungary	Published UIST 2001	LetterWise: Prefix-based Disambiguation for Mobile Text Input. I. Scott MacKenzie, Hedy Kober, Derek Smith, Terry Jones, and Eugene Skepner. We conducted a longitudinal study to compare LetterWise to MultiTap, the conventional text entry method for mobile phones. The experiment showed that the mean entry speed was 36% faster with LetterWise than with Multitap. Published in the proceedings of the The 14th Annual ACM Symposium on User Interface Software and Technology (UIST), November 2001, Orlando, Florida
Unpublished	Reviewer and User Identified problems with T9 and eZi Text Eatoni Staff Reports by profesional phone reviewers, as well as end users, which express negative reactions to AOL's T9 and Zi Corporation's eZi Text predictive text entry software.	Unpublished	Linguistically Optimized Text Entry on a Cell Phone. Hedy Kober, Eugene Skepner, Terry Jones, Howard Gutowitz, and Scott MacKenzie. A mathematical model which shows why word-guessing methods can be slower than multi-tap. If you make any kind of error while entering a word, the word "blows up". Eatoni's LetterWise and WordWise do not have this problem.	Unpublished	A Survey of Alternate Text-Entry Methods. Eatoni Staff Compares predictive text to other text-entry methods, notably voice and handwriting recognition.