Automatically classifying familiar web users from eye-tracking data: a machine learning approach

Authors: MELİH ÖDER, ŞÜKRÜ ERASLAN, YELİZ YESİLADA

Abstract: Eye-tracking studies typically collect enormous amount of data encoding rich information about user behaviours and characteristics on the web. Eye-tracking data has been proved to be useful for usability and accessibility testing and for developing adaptive systems. The main objective of our work is to mine eye-tracking data with machine learning algorithms to automatically detect users' characteristics. In this paper, we focus on exploring different machine learning algorithms to automatically classify whether users are familiar or not with a web page. We present our work with an eye-tracking data of 81 participants on six web pages. Our results show that by using eye-tracking features, we are able to classify whether users are familiar or not with a web page with the best accuracy of approximately 72% for raw data. We also show that with a resampling technique this accuracy can be improved more than 10%. This work paves the way for using eye-tracking data for identifying familiar users that can used for different purposes, for example, it can be used to better locate certain elements on pages such as adverts to meet the users' needs or it can be used to do better profiling of users for usability and accessibility assessment of pages.

Keywords: Human computer interaction, world wide web, online advertising, machine learning, eye-tracking

Full Text: PDF