Diagnostic and accessibility based user modelling

Abstract

This chapter discusses application driven user modelling by dividing user model applications into two broad categories: to provide access for the user with a device and to derive conclusions about the user. Both imply different requirements and different algorithms. The chapter starts by reviewing user modelling literature. Next, the chapter focuses on a discussion of design work in providing accessible documents to deliver accessible educational materials to students, matched to their needs and the capabilities of the device that they are using, so modelling components need to be considered.Next is a presentation of user models supporting the diagnosis of cognitive states, employing a usermodel that is expressed as fusion of sensor data. With a baseline created, the system captures sensor data over time and compares it with 'normal' pattern, to identify indications of Mild Cognitive Impairment (MCI). Finally, a novel framework for UserModels design is shown, dividing user data into static and dynamic types.