Identifying user activities using eye tracking data, mouse events, and keystrokes

Abstract

A computing device classifies user activities for a person interacting with a computer user interface using one or more user interface devices. The computing device receives eye tracking data for the person, which includes a sequence of fixations ordered temporally. Each fixation corresponds to a plurality of consecutive measured gaze points. Each fixation has a duration and location based on the corresponding gaze points. For each fixation, the computing device determines a plurality of features for the fixation, including characteristics of the fixation, context features based on preceding or subsequent fixations, and user interaction features based on information from the user interface devices during the fixation. The computing device assigns a user activity label to the fixation according to the features. The label is selected from a predefined set. The computing device then analyzes the fixations and their assigned user activity labels to make recommendations.