Predictive text encourages predictable writing
Abstract
Intelligent text entry systems, including the now-ubiquitous predictive keyboard, can make text entry more efficient, but little is known about how these systems affect the content that people write. To study how predictive text systems affect content, we compared image captions written with different kinds of predictive text suggestions. Our key findings were that captions written with suggestions were shorter and that they included fewer words that that the system did not predict. Suggestions also boosted text entry speed, but with diminishing benefit for faster typists. Our findings imply that text entry systems should be evaluated not just by speed and accuracy but also by their effect on the content written.
Integrity signals
Registry
Cites
Statistics
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?
Writing with suggestions correlates with shorter and more predictable texts being written, along with increased use of standard phrases when writing with a language model.
“Writing with suggestions correlates with shorter and more predictable texts being written [4], along with increased use of standard phrases when writing with a language model [17, 27].”
From Co-Writing with Opinionated Language Models Affects Users’ Views (2023) · cites this paper as [4]
Arnold et al. observed that suggesting single words led writers to use vocabulary from the suggestions instead of generating words themselves.
“In a separate study, Arnold et al. [19] also observed that suggesting single words led to writers using vocabulary presented by the suggestions instead of coming up with words themselves.”
From Interacting with Next-Phrase Suggestions: How Suggestion Systems Aid and Influence the Cognitive Processes of Writing (2023) · cites this paper as [19]
Predictive text encourages predictable writing in the context of single-word suggestions given by smartphone keyboards.
“Arnold et al. found that 'predictive text encourages predictable writing' [4] in the context of singleword suggestions given by smartphone keyboards.”
From Homogenization Effects of Large Language Models on Human Creative Ideation (2024) · cites this paper as [4]
The citation lists haven’t been fetched yet
References 51 · Cited by 87
- Authors
- Arnold, K. C., Chauncey, K., & Gajos, K. Z.
- Affiliations
- Calvin University (US)
- Charles River Analytics (United States) (US)
- Harvard University (US)
- Venue
- Proceedings of the 25th International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2020-03-17
- Pages
- 128-138
- OpenAlex
- W3010063553
- Cited by
- 87
- References
- 51
- Citations by year
- 2026: 15 · 2025: 17 · 2024: 19 · 2023: 13 · 2022: 8 · 2021: 12 · 2020: 3
- FWCI
- 6.58
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Conference on Intelligent User Interfaces (IUI) (publishedVersion)
- Funders
- Draper
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Physical Sciences › Computer Science › Human-Computer Interaction › Digital Communication and Language
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- text prediction, text entry, image captions, content authoring, text entry speed, word prediction
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
