Document Classification on Relevance: A Study on Eye Gaze Patterns for Reading
This paper presents a study that investigates the connection between the way that people read and the way that they understand content. The experiment consisted of having participants read some information on selected documents while an eye-tracking system recorded their eye movements. They were then asked to answer some questions and complete some tasks, on the information they had read. With the intention of investigating effective analysis approaches, both statistical methods and Artificial Neural Networks (ANN) were applied to analyse the collected gaze data in terms of several defined measures regarding the relevance of the text. The results from the statistical analysis do not show any significant correlations between those measures and the relevance of the text. However, good classification results were obtained by using an Artificial Neural Network. This suggests that using advanced learning approaches may provide more insightful differentiations than simple statistical methods particularly in analysing eye gaze reading patterns.
KeywordsDocument Classification Relevance Gaze Pattern Reading Behavior Statistical Analysis Artificial Neural Networks
Unable to display preview. Download preview PDF.
- 1.Compbell, C.S., Maglio, P.P.: A Rbust Algorithm for Reading Detection. In: 2001 Workshop on Perceptive User Interfaces, vol. 15, pp. 1–7. ACM (2001)Google Scholar
- 3.Koczy, L.T., Vamos, T., Biro, G.: Fuzzy Signatures. In: Proceedings of the 4th Meeting of the Euro Working Group on Fuzzy Sets and the 2nd International Conference on Soft and Intelligent Computing (EUROPUSE-SIC 1999), Budapest, Hungary, pp. 210–217 (1999)Google Scholar
- 5.Seeingmachines, Inc: FaceLAB (2011), http://www.seeingmachines.com/faceLAB.html
- 7.Zhu, D., Gedeon, T., Taylor, K.: Keyboard before Head Tracking Depresses User Success in Remote Camera Control. In: Gross, T., Gulliksen, J., Kotzé, P., Oestreicher, L., Palanque, P., Prates, R.O., Winckler, M. (eds.) INTERACT 2009. LNCS, vol. 5727, pp. 319–331. Springer, Heidelberg (2009)CrossRefGoogle Scholar