Data Mining Based User Modeling Systems for Web Personalization Applied to People with Disabilities

This position paper tackles the problem of automatic web personalization using machine learning techniques to model the users' behavior. The target population is people with physical, sensory or cognitive restrictions. In this paper we present our plans to study the possibility of creating user models using the information extracted from web navigation logs by means of data mining methods. We discuss the expected advantages of adopting data mining to generate information about the user, in comparison with traditional methods.