Efficacy of the Word Prediction Algorithm in WordQ
By Nantais, Tom; Shein, Fraser; Johansson, Mattias; RESNA 2001: Annual Conference Proceedings, Vol. 21, No. 1, pp. 77-79Publication Date: June 2001
Paper describing simulations to test the prediction algorithm in WordQ, a word prediction program designed for use by individuals with dyslexia and other learning disabilities to reduce the physical demands of typing. The research compiled in this paper attempted to estimate performance statistics for WordQ. Specifically, the authors are concerned with keystroke savings, number of correct keystrokes the user must supply before the correct prediction is made, and how these results depend on the main components of WordQ's use of word-pair knowledge and adaptation. WordQ was shown to eliminate approximately half of the required keystrokes, with word pair information playing an important role, and adaptation playing a lesser role, except when the text is on a very specialized subject. These are the results of a simulation, and the authors contend that testing with actual users is the only way to get an appropriate rating of effectiveness.
Assistive Products Discussed: WORDQ WRITING AID SOFTWARE
Published by: Rehabilitation Engineering & Assistive Technology Society of North America (RESNA) (Website:http://www.resna.org)
ISBN: 0-932101-43-7
This publication is included in the library of the National Rehabilitation Information Center (NARIC), accession number O14154
