Encoding decisions and expertise in the operator's eyes: Using eye-tracking as input for system adaptation

Abstract

We investigated the possibility of developing a decision support system (DSS) that integrates eye-fixation measurements to better adapt its suggestions. Indeed, eye fixation give insight into human decision-making: Individuals tend to pay more attention to key information in line with their upcoming selection. Thus, eye-fixation measures can help the DSS to better capture the context that determines user decisions. Twenty-two participants performed a simplified Air Traffic Control (ATC) simulation in which they had to decide to accept or to modify route suggestions according to specific parameter values displayed on the screen. Decisions and fixation times on each parameter were recorded. The user fixation times were used by an algorithm to estimate the utility of each parameter for its decision. Immediately after this training phase, the algorithm generated new route suggestions under two conditions: 1) Taking into account the participant's decisions, 2) Taking into account the participant's decisions plus their visual behavior using the measurements of dwell times on displayed parameters. Results showed that system suggestions were more accurate than the base system when taking into account the participant's decisions, and even more accurate using their dwell times. Capturing the crucial information for the decision using the eye tracker accelerated the DSS learning phase, and thus helped to further enhance the accuracy of consecutive suggestions. Moreover, exploratory eye-tracking analysis reflected two different stages of the decision-making process, with longer dwell times on relevant parameters (i.e. involved in a rule) during the entire decision time course, and frequency of fixations on these relevant parameters that increased, especially during the last fixations prior to the decision. Consequently, future DSS integrating eye-tracking data should pay specific care to the final fixations prior to the decision. In general, our results emphasize the potential interest of eye-tracking to enhance and accelerate system adaptation to user preference, knowledge, and expertise.