ComputingComputer ScienceDesignHuman-computer InteractionInteraction DesignUser Experience DesignAdaptive Input DevicesAdaptive InterfacesAdaptive User InterfacesInterface DesignMobile Human-computer InteractionPersonalizationClassification ModelsElectronic KeyboardsKeyboard InputOn-screen Keyboard DesignSession-based EvaluationUser Session AnalysisUser-specific Interface Adaptation
Although typing on touchscreens is slower than typing on physical keyboards, touchscreens offer a critical potential advantage: they are software-based, and, as such, the keyboard layout and classification models used to interpret key presses can dynamically adapt to suit each user's typing pattern. To explore this potential, we introduce and evaluate two novel personalized keyboard interfaces, both of which adapt their underlying key-press classification models. The first keyboard also visually adapts the location of keys while the second one always maintains a visually stable rectangular layout. A three-session user evaluation showed that the keyboard with the stable rectangular layout significantly improved typing speed compared to a control condition with no personalization. Although no similar benefit was found for the keyboard that also offered visual adaptation, overall subjective response to both new touchscreen keyboards was positive. As personalized keyboards are still an emerging area of research, we also outline a design space that includes dimensions of adaptation and key-press classification features.
33
Wrappers for feature subset selection
Ron Kohavi, George H. John · Artificial Intelligence · 1997 · 8.9K citations
Per-Ola Kristensson, Shumin Zhai · 2004 · 414 citations
The design and evaluation of a high-performance soft keyboard
I. Scott MacKenzie, Shawn X. Zhang · 1999 · 414 citations · Full text
Computing, Computer Science, Design +12