On Suggesting Phrases vs. Predicting Words for Mobile Text Composition

Arnold, Kenneth C.; Gajos, Krzysztof Z.; Kalai, Adam Tauman

doi:10.1145/2984511.2984584

Cited by 45 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms and AI-based methods (e.g., natural language processing) are widely used in current typing applications: 1) to detect typos and grammar mistakes and 2) to prevent those issues from appearing in the final text [12]. Arif et al [8] used Levenshtein distance [30] to calculate the nearest position for their smart error correction technique.…”

Section: Error Correctionmentioning

confidence: 99%

Swap: A Replacement-based Text Revision Technique for Mobile Devices

Sarcar

Kim

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Text revision is an important task to ensure the accuracy of text content. Revising text on mobile devices is cumbersome and time-consuming due to the imprecise caret control and the repetitive use of the backspace. We present Swap, a novel replacement-based technique to facilitate text revision on mobile devices. We conducted two user studies to validate the feasibility and the effectiveness of Swap compared to traditional text revision techniques. Results showed that Swap reduced efforts in caret control and repetitive backspace pressing during the text revision process. Most participants preferred to use the replacement-based technique rather than backspace and caret. They also commented that the new technique is easy to learn, and it makes text revision rapid and intuitive.

show abstract

Section: Error Correctionmentioning

confidence: 99%

Swap: A Replacement-based Text Revision Technique for Mobile Devices

Sarcar

Kim

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…They also affect user perception of text entry system quality. Additionally, the visibility of suggestions can increase both perception and interaction costs, which could reduce text entry speed, e.g., [21,40], and in some cases seems to even decrease writing accuracy [7].…”

Section: Predictive Featuresmentioning

confidence: 99%

The Effects of Predictive Features of Mobile Keyboards on Text Entry Speed and Errors

Alharbi

Stuerzlinger

Putze

2020

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Mobile users rely on typing assistant mechanisms such as prediction and autocorrect. Previous studies on mobile keyboards showed decreased performance for heavy use of word prediction, which identifies a need for more research to better understand the effectiveness of predictive features for different users. Our work aims at such a better understanding of user interaction with autocorrections and the prediction panel while entering text, in particular when these approaches fail. We present a crowd-sourced mobile text entry study with 170 participants. Our mobile web application simulates autocorrection and word prediction to capture user behaviours around these features. We found that using word prediction saves an average of 3.43 characters per phrase but also adds an average of two seconds compared to actually typing the word, resulting in a negative effect on text entry speed. We also identified that the time to fix wrong autocorrections is on average 5.5 seconds but that autocorrection does not have a significant effect on typing speed.

show abstract

“…[11] proposed a new technique for automatic word prediction based on content mining specially designed for the big data systems. Kenneth et al [12] introduced an extension for smartphone keyboard. When user tapped on keyboard, different phrase suggestions appeared on user keyboard.…”

Section: Literature Reviewmentioning

confidence: 99%

Effective Word Prediction in Urdu Language Using Stochastic Model

2018

SJCMS

View full text Add to dashboard Cite

Word prediction and word suggestion is an important tools for writing contents in any language, in which the right word is predicted in a current context. Writing contents on English keyboards to produce other language contents is too hard and time consuming for everyone and requires more practice. To increase the typing speed especially in mobile and smart phones or for creating contents on social networks derived the need of this tool in every language. This paper presents a state of the art research for word prediction in Urdu Language (UL) based on stochastic model. Hidden Markov Model was implemented to predict the next state, while Unigram Model was also used to suggest the current state and the next hidden state, N-Gram Model was followed keeping N=2. The tool is developed to implement this model for Urdu Language (UL) and tested by regular and new URDU content writers to check their improvements in their typing speeds.

show abstract

On Suggesting Phrases vs. Predicting Words for Mobile Text Composition

Cited by 45 publications

References 34 publications

Swap: A Replacement-based Text Revision Technique for Mobile Devices

Swap: A Replacement-based Text Revision Technique for Mobile Devices

The Effects of Predictive Features of Mobile Keyboards on Text Entry Speed and Errors

Effective Word Prediction in Urdu Language Using Stochastic Model

Contact Info

Product

Resources

About