Text 2.0 author tools : Robust gaze - based objective quality measures for text / Mostafa Elhosseiny ; Supervised Slim Abdennadher , Ralf Biedert

Thesis (M.Sc.) - German University - Faculty of Postgraduate Studies and Scientific Research - Department of Computer Science and Engineering

Eye tracking devices integrated in e-book readers; an increasingly likely eventuality due to recent trends, will allow us to aggregate the reading data of multiple readers in order to provide authors and editors with objective and implicitly gathered quality feedback. In this thesis we improve an initial system that is able to classify the comprehensibility of text automatically by employing machine learning techniques with an overall accuracy of 62%, an inaccurate figure due to an error in the evaluation of the initial system which exaggerated its true accuracy of 54%