User Interaction with Word Prediction: The Effects of Prediction Quality
The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
Word prediction systems can reduce the number of keystrokes required to form a message in a letter-based AAC system. It has been questioned, however, whether such savings translate into an enhanced communication rate due to the additional overhead (e.g., shifting of focus and repeated scanning of a prediction list) required in using such a system. Our hypothesis is that word prediction has high potential for enhancing AAC communication rate, but the amount is dependent in a complex way on the accuracy of the predictions. Due to significant user interface variations in AAC systems and the potential bias of prior word prediction experience on existing devices, this hypothesis is difficult to verify. We present a study of two different word prediction methods compared against letter-by-letter entry at simulated AAC communication rates. We find that word prediction systems can in fact speed communication rate (an advanced system gave a 58.6% improvement), and that a more accurate word prediction system can raise the communication rate higher than is explained by the additional accuracy of the system alone due to better utilization (93.6% utilization for advanced versus 78.2% for basic).
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In ideal cases, word prediction has been shown to improve typing speed by more than 50 percent [34].”
From “The less I type, the better”: How AI Language Models can Enhance or Impede Communication for AAC Users (2023) · cites this paper as [34]
Citations
Cites
Foundations of statistical natural language processing
Manning, C. D., & Schütze, H. (1999) · Cited by 9,816
Speech and language processing
(2010) · Day-to-Day Dyslexia in the Classroom · doi:10.4324/9780203461891_chapter_3 · Cited by 3,544
(1992) · doi:10.5555/176313.176316 · Cited by 2,892
Estimation of probabilities from sparse data for the language model component of a speech recognizer
Katz, S. (1987) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1987.1165125 · Cited by 1,637
Beukelman, D. R., & Mirenda, P. (2006) · Medical Entomology and Zoology · Cited by 757
Koehn, P., & Hoang, H. T. (2007) · The Association for Computational Linguistics · Cited by 673
Text prediction systems: a survey
Garay-Vitoria, N., & Abascal, J. (2005) · Universal Access in the Information Society · doi:10.1007/s10209-005-0005-9 · Cited by 172
Deterministic parsing of syntactic non-fluencies
Hindle, D. (1983) · Proceedings of the 21st annual meeting on Association for Computational Linguistics - · doi:10.3115/981311.981336 · Cited by 134
Modeling the speed of text entry with a word prediction interface
Koester, H. H., & Levine, S. P. (1994) · IEEE Transactions on Rehabilitation Engineering · doi:10.1109/86.331567 · Cited by 105
Demasco, P. W., & McCoy, K. F. (1992) · Communications of the ACM · doi:10.1145/129875.129881 · Cited by 103
Self-citationTHE PRACTICAL VALUE OF N-GRAMS IS IN GENERATION
Langkilde-Geary, I., & Knight, K. K. (1998) · Natural Language Generation · Cited by 95
Effect of a word prediction feature on user performance
Koester, H. H., & Levine, S. P. (1996) · Augmentative and Alternative Communication · doi:10.1080/07434619612331277608 · Cited by 90
The Effects of Word Completion and Word Prediction on Typing Rates Using On-Screen Keyboards
Anson, D. K., Moist, P., Przywara, M., Wells, H., Saylor, H., & Maxime, H. (2006) · Assistive Technology · doi:10.1080/10400435.2006.10131913 · Cited by 88
Augmented and alternative NLP techniques for augmentative and alternative communication
Copestake, A. (1997) · Cited by 68
Koester, H. H., & Levine, S. P. (1994) · Assistive Technology · doi:10.1080/10400435.1994.10132226 · Cited by 66
The rôle of natural language processing in alternative and augmentative communication
NEWELL, A., LANGER, S., & HICKEY, M. (1998) · Natural Language Engineering · doi:10.1017/s135132499800182x · Cited by 61
Effect of the “PAL” word prediction system on the quality and quantity of text generation
Newell, A. F., Arnott, J., Booth, L., Beattie, W., Brophy-Arnott, B., & Ricketts, I. W. (1992) · Augmentative and Alternative Communication · doi:10.1080/07434619212331276343 · Cited by 59
A commonsense approach to predictive text entry
Stocky, T., Faaborg, A. J., & Lieberman, H. A. (2004) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/985921.986014 · Cited by 54
Semantic knowledge in word completion
Li, J., & Hirst, G. (2005) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/1090785.1090809 · Cited by 52
Testing the efficacy of part-of-speech information in word completion
Fazly, A., & Hirst, G. (2003) · doi:10.3115/1628195.1628197 · Cited by 49
Topic modeling in fringe word prediction for AAC
Trnka, K., Yarrington, D. M., McCoy, K. T., & Pennington, C. A. (2006) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/1111449.1111509 · Cited by 49
Self-citationProfet, A New Generation of Word Prediction: An Evaluation Study
Carlberger, A., Carlberger, J., Magnuson, T., Hunnicutt, M. S., Palazuelos-Cagigas, S. E., & Navarro, S. A. (1997) · Cited by 48
Model simulations of user performance with word prediction
Koester, H. H., & Levine, S. P. (1998) · Augmentative and Alternative Communication · doi:10.1080/07434619812331278176 · Cited by 47
Garay-Vitoria, N., & Abascal, J. (1997) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/238218.238333 · Cited by 46
Efficiency of lexical prediction as a communication acceleration technique
Venkatagiri, H. (1993) · Augmentative and Alternative Communication · doi:10.1080/07434619312331276561 · Cited by 46
Methods to integrate a language model with semantic information for a word prediction componentPreprint
Wandmacher, T., & Antoine, J.-Y. (2008) · arXiv (Cornell University) · doi:10.48550/arxiv.0801.4716 · Cited by 44
The effects of word prediction on communication rate for AAC
Trnka, K., Yarrington, D., McCaw, J., McCoy, K. F., & Pennington, C. (2007) · Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX - NAACL '07 · doi:10.3115/1614108.1614152 · Cited by 41
Self-citationHorstmann, H. M., & Levine, S. P. (1990) · Augmentative and Alternative Communication · doi:10.1080/07434619012331275514 · Cited by 37
Keystroke-level models for user performance with word prediction
Koester, H. H., & Levine, S. P. (1997) · Augmentative and Alternative Communication · doi:10.1080/07434619712331278068 · Cited by 36
THE LANGUAGE COMPONENT OF THE FASTY TEXT PREDICTION SYSTEM
Trost, H., Matiasek, J., & Baroni, M. (2005) · Applied Artificial Intelligence · doi:10.1080/08839510500191901 · Cited by 33
Improving word prediction using Markov models and Heuristic methods
Hunnicutt, S., & Carlberger, J. (2001) · Augmentative and Alternative Communication · doi:10.1080/aac.17.4.255.264 · Cited by 32
Effect of window size on rate of communication in a lexical prediction AAC system
Venkatagiri, H. (1994) · Augmentative and Alternative Communication · doi:10.1080/07434619412331276810 · Cited by 31
From letters to words: efficient stroke-based word completion for trackball text entry
Wobbrock, J. O., & Myers, B. A. (2006) · Proceedings of the 8th international ACM SIGACCESS conference on Computers and accessibility · doi:10.1145/1168987.1168990 · Cited by 30
SIBYLLE: a system for alternative communication adapting to the context and its user
Wandmacher, T., Antoine, J.-Y., & Poirier, F. (2007) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/1296843.1296878 · Cited by 28
Exploiting long distance collocational relations in predictive typing
Matiasek, J., & Baroni, M. (2003) · doi:10.3115/1628195.1628196 · Cited by 26
A Comparison of Prediction Techniques to Enhance the Communication Rate
Garay-Vitoria, N., & Abascal, J. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30111-0_35 · Cited by 22
Wandmacher, T., & Antoine, J.-Y. (2006) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/593s6zeeknin · Cited by 20
DOMAIN-SPECIFIC WORD PREDICTION FOR AUGMENTATIVE COMMUNICATION
Lesher, G. W. (2001) · Cited by 19
Semantic n-gram language modeling with the latent maximum entropy principle
Wang, S., Schuurmans, D., Peng, F., & Zhao, Y. (2003) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2003.1198796 · Cited by 17
First User Test Results with the Predictive Typing System FASTY
Beck, C., Seisenbacher, G., Edelmayer, G., & Zagler, W. L. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-27817-7_120 · Cited by 14
Word prediction and communication rate in AAC
Trnka, K., McCaw, J., Yarrington, D. M., McCoy, K. F., & Pennington, C. A. (2008) · Cited by 14
Self-citationA model of performance cost versus benefit for augmentative communication systems
Koester, H. H., & Levine, S. P. (2005) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.1993.979147 · Cited by 6
Semantic & syntactic context-aware text entry methods
Gong, J. (2007) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/1296843.1296903 · Cited by 6
Research works printed but not linked: 6
- Carlberger , J. and Hunnicutt , S . 1998. A probabilistic word prediction program . In Proceedings of the RESNA Conference, 50--52 . Carlberger, J. and Hunnicutt, S. 1998. A probabilistic word prediction program. In Proceedings of the RESNA Conference, 50--52.
- Demasco , P. , McCoy , K. , Gong , Y. , Pennington , C. , and Rowe , C . 1989. Towards more intelligent AAC interfaces: The use of natural language processing . In Proceedings of the 12th Annual Conference. RESNA, 141--142 . Demasco, P., McCoy, K., Gong, Y., Pennington, C., and Rowe, C. 1989. Towards more intelligent AAC interfaces: The use of natural language processing. In Proceedings of the 12th Annual Conference. RESNA, 141--142.
- Horstmann , H. and Levine , S . 1991. The effectiveness of word prediction . In Proceedings of the RESNA Conference , vol. 11 . 100--102. Horstmann, H. and Levine, S. 1991. The effectiveness of word prediction. In Proceedings of the RESNA Conference, vol. 11. 100--102.
- Todman , J. and Alm , N. 1997 . Talk boards for social conversation . Commun. Matters 11 , 13 -- 15 . Todman, J. and Alm, N. 1997. Talk boards for social conversation. Commun. Matters 11, 13--15.
- Trnka K. Yarrington D. McCoy K. and Pennington C. 2006b. Topic modeling in fringe word prediction for AAC. In International Society for Augmentative and Alternative Communication (ISAAC). Trnka K. Yarrington D. McCoy K. and Pennington C. 2006b. Topic modeling in fringe word prediction for AAC. In International Society for Augmentative and Alternative Communication (ISAAC) . · DOI
- Yang , G. , McCoy , K. , and Demasco , P . 1990. Word prediction using a systemic tree adjoining grammar . In Proceedings of the RESNA Conference, 185--186 . Yang, G., McCoy, K., and Demasco, P. 1990. Word prediction using a systemic tree adjoining grammar. In Proceedings of the RESNA Conference, 185--186.
Cited by
How do People Type on Mobile Devices?: Observations from a Study with 37,000 Volunteers
Palin, K., Feit, A. M., Kim, S., Kristensson, P. O., & Oulasvirta, A. (2019) · Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3338286.3340120 · Cited by 190
Predictive Spelling With a P300-Based Brain–Computer Interface: Increasing the Rate of Communication
Ryan, D. B., Frye, G. E., Townsend, G., Berry, D. R., Mesa-G, S., Gates, N. A., & Sellers, E. W. (2010) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2011.535754 · Cited by 155
A Cost-Benefit Study of Text Entry Suggestion Interaction
Quinn, P., & Zhai, S. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858305 · Cited by 98
Helping the Helper : Supporting Peer Counselors via AI-Empowered Practice and Feedback
Hsu, S.-L., Shah, R. S., Senthil, P., Ashktorab, Z., Dugan, C., Geyer, W., & Yang, D. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710993 · Cited by 112
Buschek, D., Zürn, M., & Eiband, M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445372 · Cited by 108
Metadata
- Authors
- Trnka, K., McCaw, J., Yarrington, D., McCoy, K. F., & Pennington, C.
- Affiliations
- University of Delaware (US)
- AgoraNet, Inc.
- Venue
- ACM Transactions on Accessible Computing
- Published
- 2009-02
- Volume
- 1
- Issue
- 3
- Pages
- 1-34
- ISSN
- 1936-7228 (ISSN-L)
- 1936-7236
- OpenAlex
- W2018260704
- Cited by
- 93
- References
- 44
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 3 · 2023: 6 · 2022: 4 · 2021: 7 · 2020: 6 · 2019: 7 · 2018: 1 · 2017: 3 · 2016: 6 · 2015: 4 · 2014: 4 · 2013: 4 · 2012: 13
- FWCI
- 25.83
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Accessible Computing (publishedVersion)
- Funders
- U.S. Department of Education (H113G040051)
- Topics
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Keywords
- word prediction, augmentative and alternative communication, communication rate, prediction accuracy, user interface design, keystroke savings
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.