Hide/Show Apps

Mining eyetracking data to characterise users and theirpatterns of use

Download
2019
Öder, Melih
Eye tracking studies typically collect an enormous amount of data that encodes a lot of information about the users’ behavior and characteristics on the web. However, there are not many studies that mine such data to learn and discover user characteristics and profiles. The main goal of this study is to mine eye tracking data by machine learning methods to create data models which characterise users and predict their characteristics, in particular, familiarity and gender. Detecting users’ characteristics can be used in creating adaptive user interfaces to improve user experience and interaction efficiency. In a typical eye tracking study, collected demographics data have participants’ educational backgrounds, gender, age, and frequency of the web page use. In this thesis, a model focusing on the users’ familiarity degree and gender is first created based on an existing eye-tracking dataset, and then a new eye-tracking study is conducted to validate this model. The main contribution of this thesis is a machine learning approach that can be used to characterise users, in particular, familiarity and gender, based on eye-tracking data and also a tool that can be used to extract features and metrics from an eye-tracking dataset.