Typing Efficiency and Suggestion Accuracy Influence the Benefits and Adoption of Word Suggestions

Quentin Roy (1) , Sébastien Berlioux (1) , Géry Casiez (2) , Daniel Vogel (1)

1 University of Waterloo [Waterloo]
2 LOKI - Technology and knowledge for interaction

Suggesting words to complete a given sequence of characters isa common feature of typing interfaces. Yet, previous studies havenot found a clear benefit, some even finding it detrimental. Wereport on the first study to control for two important factors, wordsuggestion accuracy and typing efficiency. Our accuracy factor isenabled by a new methodology that builds on standard metrics ofword suggestions. Typing efficiency is based on device type. Resultsshow word suggestions are used less often in a desktop condition,with little difference between tablet and phone conditions. Veryaccurate suggestions do not improve entry speed on desktop, but doon tablet and phone. Based on our findings, we discuss implicationsfor the design of automation features in typing systems.

Mots clés: Text-entry; Word prediction; Human-Computer Interaction

Domaines: Interface homme-machine [cs.HC]

Quentin Roy, Sébastien Berlioux, Géry Casiez, Daniel Vogel. Typing Efficiency and Suggestion Accuracy Influence the Benefits and Adoption of Word Suggestions. CHI 2021 - Conference on Human Factors in Computing Systems, May 2021, Yokohama / Virtual, Japan. ⟨10.1145/3411764.3445725⟩. ⟨hal-03172202⟩