Advertisement

Evaluation and Optimization of Word Disambiguation for Text-Entry Methods

  • Hamed  H. SadEmail author
  • Franck Poirier
Conference paper

Abstract

We study the key-characters assignment on ambiguous keyboards. We consider two cases: unconstrained and alphabetically constrained character arrangements on ambiguous keys. A genetic algorithm is used for searching the assignment that optimizes the text-entry performance. The results show that as the number of keys decreases, the gain in performance due to optimization increases. We also study the effect of the disambiguation word list layout on the text-entry usability. We demonstrate that adding words by completion to the word list always leads to better performance. The usability effect of changing the number of ambiguous keys, compared to changing the number of words displayed to the user, is investigated.

Keywords

Mobile Device Word List Text Entry Candidate Word Standard Telephone 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Silfverberg M, et al. (2000) Predicting text entry speed on mobile phones. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (The Hague, The Netherlands, 2000). ACM, New York, NY, pp. 9–16, doi: http://doi.acm.org/10.1145/332040.332044
  2. 2.
    Poirier F and Belatar M (2006) Évaluation d’analogies scripturales pour la conception d’une méthode de saisie en mobilité – Uni-Glyph. Ergo-IA: 333–336Google Scholar
  3. 3.
    Zhai S, et al. (2002) Movement model, hits distribution and learning in virtual keyboarding. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems: Changing Our World, Changing Ourselves (Minneapolis, MN, April 20–25, 2002). ACM, New York, NY, pp. 17–24, doi: http://doi.acm.org/10.1145/503376.503381
  4. 4.
    James CL and Reischel KM (2001) Text input for mobile devices: comparing model prediction to actual performance. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (Seattle, WA, 2001). ACM, New York, NY, pp. 365–371, doi: http://doi.acm.org/10.1145/365024.365300
  5. 5.
    Rosenfeld R (2000) Two decades of statistical language modeling: where do we go from here? Proc. IEEE 88: 1270–1278CrossRefGoogle Scholar
  6. 6.
    Lesher GW, et al (1998) Optimal character arrangements for ambiguous keyboards. IEEE Trans. Rehabil. Eng. (see also IEEE Trans. Neural Syst. Rehabil. Eng.) 6: 415–423Google Scholar
  7. 7.
    Nesbat S (2003) A system for fast, full-text entry for small electronic devices. In Proceedings of the 5th international conference on Multimodal interfaces (Vancouver, BC, 2003). ACM, New York, NY, pp. 4–11, doi: http://doi.acm.org/10.1145/958432.958437
  8. 8.
    Tanaka-Ishii K, et al. (2002) Entering text with a four-button device. In Proceedings of the 19th International Conference on Computational Linguistics – Volume 1 (Taipei, Taiwan, 2002). Association for Computational Linguistics, Morristown, NJ, pp. 988–994Google Scholar
  9. 9.
    Gong J and Tarasewich P (2005) Alphabetically constrained keypad designs for text entry on mobile devices. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. doi: http://doi.acm.org/10.1145/1054972.1055002
  10. 10.
    MacKenzie IS (2002) KSPC (Keystrokes per Character) as a Characteristic of Text Entry Techniques. In Proceedings of the 4th International Symposium on Mobile Human–Computer Interaction (Pisa, Italy, September 18–20, 2002). Springer, London, pp. 195–210Google Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  1. 1.Université de Bretagne-SudVALORIA – Centre de RechercheFrance

Personalised recommendations