Predicting Choice Behaviour in Economic Games using Gaze Data Encoded as Scanpath Images

Abstract

Eye movement data has been extensively utilized by researchers interested in studying decision-making within the strategic setting of economic games. In this paper, we demonstrate both a deep learning and traditional machine learning classification method which are able to accurately identify a given participant's decision strategy before they commit to an action while playing games. Our approach focuses on creating scanpath images that best capture the dynamics of a participant's gaze behaviour during a given game in a way that is meaningful to the machine learning models. Our results demonstrate a higher classification accuracy compared to traditional methods of analysis applied to the same economic game environments by as much as 18 percentage points. In a broader context, we aim to illustrate the potential for eye-tracking data to create information asymmetries in strategic environments in favour of those who collect and process the data. These information asymmetries could become especially relevant as eye-tracking is expected to become more widespread in user applications, with the seemingly imminent mass adoption of virtual reality systems, and the development of devices with the ability to record eye movement outside of a laboratory setting.

Facilitating Cooperation by Manipulating Attention

“…Using machine learning, we were able to accurately predict trialby-trial cooperation from four-fixation (three first and last) gaze sequences, with higher accuracy than using the first and last fixations only, showing the importance of studying gaze sequences. Scanpaths have been used in vision research to compare information-sampling patterns across individuals 75 or to improve users' experience in human-computer interactions 76 , and they have recently been applied to predict choices in economic games 77 . Here we showed that studying such paths in the context of cooperative decisions improves predictions of behavior and allows us to explain the effects of exogenous manipulations of attention on choices, by showing how positioning options at different locations on the screen modified key information sampling patterns, not limited to the first information subjects sampled.…”