Modelling Learning of New Keyboard Layouts

@article{Jokinen2017ModellingLO,
  title={Modelling Learning of New Keyboard Layouts},
  author={Jussi P. P. Jokinen and Sayan Sarcar and Antti Oulasvirta and Chaklam Silpasuwanchai and Zhenxin Wang and Xiangshi Ren},
  journal={Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems},
  year={2017}
}
  • Jussi P. P. Jokinen, S. Sarcar, X. Ren
  • Published 2 May 2017
  • Computer Science, Psychology
  • Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems
Predicting how users learn new or changed interfaces is a long-standing objective in HCI research. This paper contributes to understanding of visual search and learning in text entry. With a goal of explaining variance in novices' typing performance that is attributable to visual search, a model was designed to predict how users learn to locate keys on a keyboard: initially relying on visual short-term memory but then transitioning to recall-based search. This allows predicting search times and… 
View on ACM
dl.acm.org
43 Citations
Highly Influential Citations
3
Background Citations
28
Methods Citations
11

Figures and Tables from this paper

43 Citations

Citation Type

Citation Type

Learning to type with mobile keyboards: Findings with a randomized keyboard
Influence of keyboard layout and feedback type in eye-typing tasks: a comparative study
TLDR
The results expand previous findings showing the advantages of deploying a circularly-shaped keyboard, and confirm the impact of visual feedback for successful performance in an eye-typing task.
Touchscreen Typing As Optimal Supervisory Control
TLDR
A unifying account of touchscreen typing is proposed, regarding it as optimal supervisory control, and a model is presented that simulates co-ordination of eye and finger movements that creates realistic finger- and eye-movement patterns and shows human-like adaptation.
I . Frequency II . Serial Position Curve III . Visual Statistical Learning IV . Cognitive Model
TLDR
Familiariser is a browser-based implementation that automatically restructures webpage layouts based on the visual history of the user, and its evaluation with users provides first evidence favouring familiarisation.
The Effects of Predictive Features of Mobile Keyboards on Text Entry Speed and Errors
TLDR
This work presents a crowd-sourced mobile text entry study with 170 participants and simulates autocorrection and word prediction to capture user behaviours around these features, finding that using word prediction saves an average of 3.43 characters per phrase but also adds two seconds compared to actually typing the word, resulting in a negative effect on text entry speed.
Familiarisation: Restructuring Layouts with Visual Learning Models
TLDR
Four concepts of familiarisation, inspired by the human visual system, are explored to automatically generate a familiar design for each user in domains where users spend excess time searching for common elements in familiar locations.
Adaptive feature guidance: Modelling visual search with graphical layouts
Exploring Low-Occlusion Qwerty Soft Keyboard Using Spatial Landmarks
The Qwerty soft keyboard is widely used on mobile devices. However, keyboards often consume a large portion of the touchscreen space, occluding the application view on the smartphone and requiring a…
Exploring Low-Occlusion Qwerty Soft Keyboard Using Spatial Landmarks
The Qwerty soft keyboard is widely used on mobile devices. However, keyboards often consume a large portion of the touchscreen space, occluding the application view on the smartphone and requiring a…
Individualising Graphical Layouts with Predictive Visual Search Models
TLDR
Evaluation of Familiariser (using visual statistical learning) with users provides first evidence that the approach reduces visual search time by over 10%, and number of eye-gaze fixations by over 20%, during web browsing tasks.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 73 REFERENCES
Movement model, hits distribution and learning in virtual keyboarding
TLDR
Increased visual load when typing previously practiced text did not significantly change users' performance at this stage of learning, but typing unpracticed text did have a performance effect, suggesting a certain degree of text specific learning when typing on virtual keyboards.
Comparing cognitive effort in spatial learning of text entry keyboards and ShapeWriters
TLDR
This paper quantitatively compares the level of cognitive effort in terms of a newly introduced parameter in the declarative memory model of a cognitive architecture, ACT-R, and theoretically compare the cognitive effort of two different layouts of graphical buttons with respect to their label representativeness in the domains of traditional keyboard and ShapeWriter.
The role of visual search in the design of effective soft keyboards
TLDR
Results are reported of an experiment that supports the claim that both familiarity and the number of letters per key must be considered when predicting visual search times for alternative keyboard layouts.
An empirical investigation of the novice experience with soft keyboards
TLDR
An experiment with 12 participants tested text entry rates on two sizes of soft keyboards with either a Qwerty layout or a layout presenting a randomized letter arrangement after each tap, rejecting a previous model of novice interaction that used Fitts' law for stylus movement and the Hick-Hyman law for visual scan time.
Top-down learning strategies: can they facilitate stylus keyboard learning?
Model of visual search and selection time in linear menus
TLDR
A novel mathematical model for visual search and selection time in linear menus that is expressed as probability density distribution of gaze, which allows for deriving total selection time and has the potential to improve menu designs by helping designers identify more effective solutions without conducting empirical studies.
Mobile devices: soft keyboard text-entry enhanced by Visual Cues
TLDR
According to the letter prediction system, visual clues could be used to improve immediate user satisfaction with optimized soft keyboard, contributing to enlarge their audience.
Quasi-qwerty soft keyboard optimization
TLDR
The results show that a middle ground between the optimized but new, and the familiar (Qwerty) but inefficient does exist, and that by allowing letters to move at most one step away from their original positions on Qwerty in an optimization process, one can achieve about half of what free optimization could gain in movement efficiency.
A predictive model of menu performance
TLDR
A model of menu performance is proposed that goes beyond previous work by incorporating components for Fitts' Law pointing time, visual search time, Hick-Hyman Law decision time when expert, and for the transition from novice to expert behaviour.
Model for non-expert text entry speed on 12-button phone keypads
TLDR
A new model for predicting text entry speed on a 12-button mobile phone keypad based on Fitts' law and a linguistic component based on letter digraph probabilities is presented.
...
1
2
3
4
5
...