Implicit Profiling for Contextual Reasoning About Users' Spatial Preferences

Information overload is a well documented problem in many application domains. A way of addressing this problem is by creating user profiles and by filtering out all irrelevant information while presenting the users only with information that matches their interests. Our focus is on the spatial domain. We follow an implicit profiling approach by logging users’ mouse movements as they interact with spatial data. The logged information is analysed to support context reasoning about each user’s level of interest in the spatial features shown to him. These inferred interests are used to calculate an interest model for each individual user. Based on this interest model we can filter the information returned to the user, reducing information overload and tailoring the content to suit the users spatial preferences. In this paper we present our approach and discuss the implementation of the system we are developing for capturing users’ spatial interactions and generating user profiles.