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

Abstract

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.

Mobile Typing with Intelligent Text Entry: A Large-Scale Dataset and Results

“…One of the key factors which affect the user's decision to utilize AC is the accuracy and the cost of error of the AC. Correcting AC errors takes more effort and time because errors are more difficult to notice and, therefore, the user decreases their typing speed to make fewer typing errors if AC has too high error rate [18,19]. when correcting AC errors takes more effort and time.…”

“…In addition to word suggestions, whole phrases can also be suggested to the user [22,23]. The SB updates the suggestions while typing, thus, regular use requires the user to switch attention from typing to the suggestions which slows the typing on average [6,9,19,24] even though typing uses fewer keystrokes [19,25]. In addition to attention shift, the selection process itself is also slow.…”

“…However, the typing strategy changes with the keyboard. When a custom keyboard is used, ITE methods are also custom made [15,19] and thus they do not perform exactly as the user is used to on their own device. Because the users adapt to the keyboards to optimize the typing experience [6], the typing changes when the keyboard or ITE method changes.…”

“…• Mobile typing dataset by 170 participants [19]. Participants typed with a custom keyboard which included Autocorrection and Suggestion Bar methods.…”