Applying information theory and entropy to eliminate errors in mouse-tracking results

TL;DR

This paper introduces an automated method using information theory and Shannon entropy to correct errors in mouse-tracking data, improving the accuracy of user gaze estimation as an alternative to eye-tracking.

Contribution

The novel approach applies entropy calculations to identify and correct discrepancies between mouse cursor and eye-gaze positions in web usability studies.

Findings

High correlation between corrected mouse and eye-gaze heat maps

Reduced Euclidean distance after correction

Visual assessments confirm improved accuracy

Abstract

Mouse-tracking of computer system users represents a less expensive, but also a far more applicable alternative to eye-tracking. The main disadvantage of mouse-tracking are errors manifested as discrepancies between the actual eye-gaze position and the mouse cursor position. This paper presents a method for automated correction of errors arising in mouse-tracking. Our approach draws upon information theory and employs Shannon entropy. The method is based on calculating the entropy of a visual representation of a Web page, i.e., we quantify information potential values of various positions. Information obtained, thereby, is paired with cumulative time intervals, spent by the mouse cursor in each position. In this way, we identify cursor positions that do not match eye-gaze positions. To verify the effectiveness of our method, we compared the eye gaze and mouse cursor heat maps in the following ways: We calculated the coefficient of correlation between the two; we computed Euclidean distance between their centers of gravity; and we performed visual comparison.