New paper accepted to the ACM Symposium on User Interface Software and Technology
Simulating Word Suggestion Usage in Mobile Typing to Guide Intelligent Text Entry Design
Yang Li, Anna Maria Feit
Abstract:
Intelligent text entry (ITE) methods, such as word suggestions, are widely used in mobile typing, yet improving these systems remains challenging because the cognitive mechanisms underlying suggestion use are poorly understood and evaluating new systems often requires long-term user studies to account for behavioral adaptation. We present WSTypist, a reinforcement learning-based model that simulates how typists integrate word suggestions into typing. We extend recent hierarchical control models of typing by identifying and implementing important cognitive mechanisms that underlie high-level decision-making when integrating word suggestions into manual typing: considering orthographic processes, assessing efficiency gains, and accounting for personal preferences regarding AI support. Our evaluations show that WSTypist simulates diverse human-like suggestion-use strategies, reproduces behavioral differences, and generalizes across different systems. Through four design cases, we demonstrate how a computational rationality model can inform what-if analyses during the design process by simulating how users might adapt to changes in the UI or algorithmic support, thereby reducing the need for user studies early in the exploratory design phase.
Link to article:
Be First to Comment